CN104809245A - Image retrieval method - Google Patents
Image retrieval method Download PDFInfo
- Publication number
- CN104809245A CN104809245A CN201510250554.1A CN201510250554A CN104809245A CN 104809245 A CN104809245 A CN 104809245A CN 201510250554 A CN201510250554 A CN 201510250554A CN 104809245 A CN104809245 A CN 104809245A
- Authority
- CN
- China
- Prior art keywords
- image
- source images
- passage
- color
- calculate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Landscapes
- Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
Description
技术领域technical field
本发明涉及信息检索技术领域，具体是一种图像检索方法。The invention relates to the technical field of information retrieval, in particular to an image retrieval method.
背景技术Background technique
随着信息技术的发展，图像检索的应用领域越发广泛，已成为不可或缺的技术，衡量图像检索算法好坏的重要指标除了准确度之外就是时间和空间复杂度。自上世纪七、八十年代开始，图像检索便成为一个非常活跃的研究领域，主要使用了基于文本的图像检索技术和基于内容的图像检索技术。With the development of information technology, the application fields of image retrieval are becoming more and more extensive, and it has become an indispensable technology. The important indicators to measure the quality of image retrieval algorithms are time and space complexity besides accuracy. Since the 1970s and 1980s, image retrieval has become a very active research field, mainly using text-based image retrieval technology and content-based image retrieval technology.
基于文本的图像检索技术(TBIR)沿用了传统文本检索技术，它难以考虑图像本身固有的颜色、纹理、形状等内容特征，而是使用关键字来描述图像，即检索的时候一般以输入关键字的形式检索相关图像。该技术存在以下两方面缺陷：首先因为现在图像数据库规模的不断膨胀，对数据库中每一副图像进行人工标注需要耗费大量的时间和人力；其次，图像内容千差万别，使用关键字难以准确描述图像的内涵，而且在人工选取关键字的过程中会包含强烈的主观性，可能造成图像理解上的偏差，直接影响图像的检索效果。Text-based image retrieval technology (TBIR) follows the traditional text retrieval technology. It is difficult to consider the inherent color, texture, shape and other content characteristics of the image itself. Instead, it uses keywords to describe the image. Retrieve related images in the form of . This technology has the following two drawbacks: firstly, due to the continuous expansion of the current image database, it takes a lot of time and manpower to manually label each image in the database; secondly, the image content varies widely, and it is difficult to accurately describe the content of the image using keywords. Connotation, and the process of artificially selecting keywords will contain strong subjectivity, which may cause deviations in image understanding and directly affect the retrieval effect of images.
基于内容的图像检索技术(CBIR)包含图像视觉特征提取和特征相似度计算两个环节。现有的基于内容的图像检索系统大部分仅采用单一的图像检索方法或仅使用一类图像特征。因此，当查询图像包含多个物体或者背景比较复杂时，会引入较大的检索错误，使得检索结果不够精确。虽然存在基于特征融合进行图像检索的方式，但特征融合的方式单一，检索效果并不理想。Content-based Image Retrieval (CBIR) includes two links: image visual feature extraction and feature similarity calculation. Most of the existing content-based image retrieval systems only use a single image retrieval method or use only one type of image features. Therefore, when the query image contains multiple objects or the background is complex, large retrieval errors will be introduced, making the retrieval results inaccurate. Although there is a method of image retrieval based on feature fusion, the method of feature fusion is single, and the retrieval effect is not ideal.
发明内容Contents of the invention
本发明的目的在于提供一种基于图像的纹理特征、边缘形状特征以及颜色特征相似度相结合的检索方法，保证了检索结果的精度。The purpose of the present invention is to provide a retrieval method based on the combination of image texture features, edge shape features and color feature similarities, which ensures the accuracy of retrieval results.
为实现上述目的，本发明提供如下技术方案：To achieve the above object, the present invention provides the following technical solutions:
一种图像检索方法，基于包括N个比对图像的图像库，包括以下步骤：An image retrieval method, based on an image library comprising N comparison images, comprising the following steps:
(1)提取源图像和图像库中每个图像的纹理特征，包括以下步骤：(1) Extract the texture feature of each image in the source image and the image library, including the following steps:
11)获取源图像和图像库中的每个图像，将源图像、图像库中每个图像调整为大小一致，将调整后的每个图像划分为m*n分区；11) Obtain each image in the source image and the image library, adjust each image in the source image and the image library to be of the same size, and divide each image after adjustment into m*n partitions;
12)针对调整后的每个图像，计算其每个分区中每个像素块的平均灰度值，依次取每个像素块的8邻域像素块，计算每个像素块的8邻域像素块的平均灰度值；根据每个像素块的平均灰度值、每个像素块的平均灰度值与其对应的8邻域像素块的平均灰度值的比值，计算每个分区的8邻域像素块的灰度离散度；12) For each adjusted image, calculate the average gray value of each pixel block in each partition, take the 8 neighboring pixel blocks of each pixel block in turn, and calculate the 8 neighboring pixel blocks of each pixel block According to the average gray value of each pixel block, the ratio of the average gray value of each pixel block to the average gray value of the corresponding 8 neighborhood pixel blocks, calculate the 8-neighborhood of each partition The gray level dispersion of the pixel block;
13)定义一致性阈值，针对每个图像的每个分区，根据灰度离散度和一致性阈值获得每个分区的特征向量；13) define the consistency threshold, for each subregion of each image, obtain the feature vector of each subregion according to the gray level dispersion and the consistency threshold;
14)根据每个图像的所有分区的特征向量获取每个图像的纹理特征；14) Obtain the texture feature of each image according to the feature vectors of all partitions of each image;
(2)计算源图像与图像库中每个图像之间的纹理特征相似度，将纹理特征相似度大于第一设定阈值的图像组合成第一图像集；(2) Calculate the texture feature similarity between the source image and each image in the image library, and combine the images with the texture feature similarity greater than the first set threshold into the first image set;
(3)采用canny算子提取源图像和第一图像集中每个图像的边缘形状特征，根据提取的边缘形状特征，对边界方向以5度为间隔来进行划分，经过划分后形成一个一共有72级的边界方向直方图，并采用公式Fi＝fi/S对边界方向直方图进行归一化处理；其中，Fi为归一化的边界方向直方图，fi为边界方向直方图；S为图像的面积；(3) The canny operator is used to extract the edge shape features of each image in the source image and the first image set. According to the extracted edge shape features, the boundary direction is divided at an interval of 5 degrees. After division, a total of 72 The boundary direction histogram of level, and adopt formula F i =f i /S to carry out normalization process to boundary direction histogram; Wherein, F i is the boundary direction histogram of normalization, f i is the boundary direction histogram; S is the area of the image;
(4)计算源图像与第一图像集中每个图像之间的边缘形状特征相似度，将边缘形状特征相似度大于第二设定阈值的图像组合成第二图像集；(4) Calculate the edge shape feature similarity between each image in the source image and the first image set, and combine the images with the edge shape feature similarity greater than the second preset threshold into the second image set;
(5)获取源图像和第二图像集中每个图像的颜色特征，包括以下步骤：(5) Obtain the color feature of each image in the source image and the second image set, comprising the following steps:
51)将源图像与第二图像集中每个图像转换为HSV图像格式，获取格式转换后的每个图像的三个通道，所述三个通道为色调通道、饱和度通道和亮度通道；51) converting each image in the source image and the second image set into an HSV image format, and obtaining three channels of each image after the format conversion, the three channels being a hue channel, a saturation channel and a brightness channel;
52)对饱和度通道进行二值化处理，得到饱和度通道的亮区域和暗区域，将饱和度通道的亮区域对色调通道进行投影获得色调通道的色调区域，以及将饱和度通道的暗区域对亮度通道进行投影获得亮度通道中与饱和度通道暗区域对应的区域，并统计色调通道中的色调区域的灰度直方图以及亮度通道中与饱和度通道暗区域的对应区域灰度直方图；52) Binarize the saturation channel to obtain the bright and dark areas of the saturation channel, project the bright area of the saturation channel to the hue channel to obtain the hue area of the hue channel, and convert the dark area of the saturation channel Project the brightness channel to obtain the region corresponding to the dark region of the saturation channel in the brightness channel, and count the grayscale histogram of the hue region in the hue channel and the grayscale histogram of the region corresponding to the dark region of the saturation channel in the brightness channel;
53)根据色调通道中的色调区域的灰度直方图设定色调数组，以及根据亮度通道中与饱和度通道暗区域的对应区域灰度直方图设定亮度数组，并根据色调数据和亮度数组获取对应图像的颜色信息；53) Set the hue array according to the grayscale histogram of the hue area in the hue channel, and set the brightness array according to the grayscale histogram of the corresponding area in the brightness channel and the dark area of the saturation channel, and obtain it according to the hue data and the brightness array The color information of the corresponding image;
54)根据图像的颜色信息获取图像的颜色向量，对图像的颜色向量进行二值化处理，根据二值化处理结果计算图像的颜色特征54) Obtain the color vector of the image according to the color information of the image, perform binarization processing on the color vector of the image, and calculate the color feature of the image according to the binarization processing result
(6)计算源图像与第二图像集中每个图像之间的颜色特征相似度，将颜色特征相似度大于第三设定阈值的图像组合成第三图像集；(6) Calculate the color feature similarity between each image in the source image and the second image set, and combine the images with the color feature similarity greater than the third preset threshold into a third image set;
(7)对第三图像集中的图像进行排列显示，包括以下步骤：(7) Arranging and displaying the images in the third image set, including the following steps:
71)根据与源图像之间的颜色特征相似度由高到低的顺序，对第三图像集中的图像进行排列显示；71) Arranging and displaying the images in the third image set according to the order of the color feature similarity with the source image from high to low;
72)当存在多个与源图像之间的颜色特征相似度相同的图像，则分别计算该多个图像与源图像之间的颜色距离，以与源图像之间的颜色距离由小到大的顺序对该多个图像进行排列显示。72) When there are multiple images with the same color feature similarity as the source image, calculate the color distance between the multiple images and the source image respectively, so that the color distance from the source image is from small to large The plurality of images are arranged and displayed sequentially.
与现有技术相比，本发明的有益效果是：Compared with prior art, the beneficial effect of the present invention is:
本发明采用图像的纹理特征、边缘形状特征以及颜色特征相似度相结合的检索方法，图像特征向量维度较低，提高了图像处理速度，从而提高了图像检索的速度，大大地提高了图像检索的准确度，保证了检索结果的精度。本发明具有计算简单、对待检索图像无需人工处理、普适性强、耦合性低等特点，增强了其用于数字图像检索的实用性。The present invention adopts the retrieval method combining image texture feature, edge shape feature and color feature similarity, the dimension of image feature vector is low, improves the image processing speed, thereby improves the speed of image retrieval, greatly improves the efficiency of image retrieval Accuracy ensures the accuracy of the retrieval results. The invention has the characteristics of simple calculation, no manual processing of images to be retrieved, strong universality, low coupling, etc., and enhances its practicability for digital image retrieval.
本发明根据边缘形状特征获得边界直方图，边界方向不会受到图像中对象位置变化的影响，具有尺度不变性，弥补了颜色直方图无法描述图像中颜色的局部分布及每种色彩所处的空间位置的确定。The invention obtains the boundary histogram according to the edge shape feature, the boundary direction will not be affected by the position change of the object in the image, has scale invariance, and makes up for the inability of the color histogram to describe the local distribution of colors in the image and the space in which each color is located location determination.
附图说明Description of drawings
图1是本发明实施例的图像检索方法的流程图。FIG. 1 is a flowchart of an image retrieval method according to an embodiment of the present invention.
具体实施方式Detailed ways
下面将结合本发明实施例及附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The following will clearly and completely describe the technical solutions in the embodiments of the present invention in combination with the embodiments of the present invention and the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
请参阅图1，本发明实施例中，一种图像检索方法，基于包括N个比对图像的图像库，包括以下步骤：Please refer to Fig. 1, in the embodiment of the present invention, a kind of image retrieval method, based on the image library that comprises N comparison images, comprises the following steps:
(1)提取源图像和图像库中每个图像的纹理特征，具体包括：(1) Extract the texture features of each image in the source image and the image library, specifically including:
11)获取源图像和图像库中的每个图像，将源图像、图像库中每个图像调整为大小一致，将调整后的每个图像划分为m*n分区；11) Obtain each image in the source image and the image library, adjust each image in the source image and the image library to be of the same size, and divide each image after adjustment into m*n partitions;
12)针对调整后的每个图像，计算其每个分区中每个像素块的平均灰度值，依次取每个像素块的8邻域像素块，计算每个像素块的8邻域像素块的平均灰度值；根据每个像素块的平均灰度值、每个像素块的平均灰度值与其对应的8邻域像素块的平均灰度值的比值，计算每个分区的8邻域像素块的灰度离散度；12) For each adjusted image, calculate the average gray value of each pixel block in each partition, take the 8 neighboring pixel blocks of each pixel block in turn, and calculate the 8 neighboring pixel blocks of each pixel block According to the average gray value of each pixel block, the ratio of the average gray value of each pixel block to the average gray value of the corresponding 8 neighborhood pixel blocks, calculate the 8-neighborhood of each partition The gray level dispersion of the pixel block;
13)定义一致性阈值，针对每个图像的每个分区，根据灰度离散度和一致性阈值获得每个分区的特征向量；13) define the consistency threshold, for each subregion of each image, obtain the feature vector of each subregion according to the gray level dispersion and the consistency threshold;
14)根据每个图像的所有分区的特征向量获取每个图像的纹理特征；14) Obtain the texture feature of each image according to the feature vectors of all partitions of each image;
(2)计算源图像与图像库中每个图像之间的纹理特征相似度，将纹理特征相似度大于第一设定阈值的图像组合成第一图像集；(2) Calculate the texture feature similarity between the source image and each image in the image library, and combine the images with the texture feature similarity greater than the first set threshold into the first image set;
(3)采用canny算子提取源图像和第一图像集中每个图像的边缘形状特征，根据提取的边缘形状特征获得边界直方图，具体为：对边界方向以5度为间隔来进行划分，经过划分后形成一个一共有72级的边界方向直方图，并采用公式Fi＝fi/S对边界方向直方图进行归一化处理；其中，Fi为归一化的边界方向直方图，fi为边界方向直方图；S为图像的面积；(3) Use the canny operator to extract the edge shape features of each image in the source image and the first image set, and obtain the boundary histogram according to the extracted edge shape features, specifically: divide the boundary direction at intervals of 5 degrees, and pass After division, a boundary direction histogram with a total of 72 levels is formed, and the formula F i =f i /S is used to normalize the boundary direction histogram; wherein, F i is the normalized boundary direction histogram, and f i is the boundary direction histogram; S is the area of the image;
(4)计算源图像与第一图像集中每个图像之间的边缘形状特征相似度，将边缘形状特征相似度大于第二设定阈值的图像组合成第二图像集；(4) Calculate the edge shape feature similarity between each image in the source image and the first image set, and combine the images with the edge shape feature similarity greater than the second preset threshold into the second image set;
(5)获取源图像和第二图像集中每个图像的颜色特征，具体包括：(5) Obtain the color feature of each image in the source image and the second image set, specifically including:
51)将源图像与第二图像集中每个图像转换为HSV图像格式，获取格式转换后的每个图像的三个通道，所述三个通道为色调通道、饱和度通道和亮度通道；51) converting each image in the source image and the second image set into an HSV image format, and obtaining three channels of each image after the format conversion, the three channels being a hue channel, a saturation channel and a brightness channel;
52)对饱和度通道进行二值化处理，得到饱和度通道的亮区域和暗区域，将饱和度通道的亮区域对色调通道进行投影获得色调通道的色调区域，以及将饱和度通道的暗区域对亮度通道进行投影获得亮度通道中与饱和度通道暗区域对应的区域，并统计色调通道中的色调区域的灰度直方图以及亮度通道中与饱和度通道暗区域的对应区域灰度直方图；52) Binarize the saturation channel to obtain the bright and dark areas of the saturation channel, project the bright area of the saturation channel to the hue channel to obtain the hue area of the hue channel, and convert the dark area of the saturation channel Project the brightness channel to obtain the region corresponding to the dark region of the saturation channel in the brightness channel, and count the grayscale histogram of the hue region in the hue channel and the grayscale histogram of the region corresponding to the dark region of the saturation channel in the brightness channel;
53)根据色调通道中的色调区域的灰度直方图设定色调数组，以及根据亮度通道中与饱和度通道暗区域的对应区域灰度直方图设定亮度数组，并根据色调数据和亮度数组获取对应图像的颜色信息；53) Set the hue array according to the grayscale histogram of the hue area in the hue channel, and set the brightness array according to the grayscale histogram of the corresponding area in the brightness channel and the dark area of the saturation channel, and obtain it according to the hue data and the brightness array The color information of the corresponding image;
54)根据图像的颜色信息获取图像的颜色向量，对图像的颜色向量进行二值化处理，根据二值化处理结果计算图像的颜色特征；54) Acquire the color vector of the image according to the color information of the image, carry out binarization processing to the color vector of the image, and calculate the color feature of the image according to the binarization processing result;
(6)计算源图像与第二图像集中每个图像之间的颜色特征相似度，将颜色特征相似度大于第三设定阈值的图像组合成第三图像集；(6) Calculate the color feature similarity between each image in the source image and the second image set, and combine the images with the color feature similarity greater than the third preset threshold into a third image set;
(7)对第三图像集中的图像进行排列显示，具体包括：(7) Arranging and displaying the images in the third image set, specifically including:
71)根据与源图像之间的颜色特征相似度由高到低的顺序，对第三图像集中的图像进行排列显示；71) Arranging and displaying the images in the third image set according to the order of the color feature similarity with the source image from high to low;
72)当存在多个与源图像之间的颜色特征相似度相同的图像，则分别计算该多个图像与源图像之间的颜色距离，以与源图像之间的颜色距离由小到大的顺序对该多个图像进行排列显示。72) When there are multiple images with the same color feature similarity as the source image, calculate the color distance between the multiple images and the source image respectively, so that the color distance from the source image is from small to large The plurality of images are arranged and displayed sequentially.
本发明采用图像的纹理特征、边缘形状特征以及颜色特征相似度相结合的检索方法，图像特征向量维度较低，提高了图像处理速度，从而提高了图像检索的速度，大大地提高了图像检索的准确度，保证了检索结果的精度。本发明具有计算简单、对待检索图像无需人工处理、普适性强、耦合性低等特点，增强了其用于数字图像检索的实用性。The present invention adopts the retrieval method combining image texture feature, edge shape feature and color feature similarity, the dimension of image feature vector is low, improves the image processing speed, thereby improves the speed of image retrieval, greatly improves the efficiency of image retrieval Accuracy ensures the accuracy of the retrieval results. The invention has the characteristics of simple calculation, no manual processing of images to be retrieved, strong universality, low coupling, etc., and enhances its practicability for digital image retrieval.
本发明根据边缘形状特征获得边界直方图，边界方向不会受到图像中对象位置变化的影响，具有尺度不变性，弥补了颜色直方图无法描述图像中颜色的局部分布及每种色彩所处的空间位置的确定。The invention obtains the boundary histogram according to the edge shape feature, the boundary direction will not be affected by the position change of the object in the image, has scale invariance, and makes up for the inability of the color histogram to describe the local distribution of colors in the image and the space in which each color is located location determination.
对于本领域技术人员而言，显然本发明不限于上述示范性实施例的细节，而且在不背离本发明的精神或基本特征的情况下，能够以其他的具体形式实现本发明。因此，无论从哪一点来看，均应将实施例看作是示范性的，而且是非限制性的，本发明的范围由所附权利要求而不是上述说明限定，因此旨在将落在权利要求的等同要件的含义和范围内的所有变化囊括在本发明内。It will be apparent to those skilled in the art that the invention is not limited to the details of the above-described exemplary embodiments, but that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Accordingly, the embodiments should be regarded in all points of view as exemplary and not restrictive, the scope of the invention being defined by the appended claims rather than the foregoing description, and it is therefore intended that the scope of the invention be defined by the appended claims rather than by the foregoing description. All changes within the meaning and range of equivalents of the elements are embraced in the present invention.
此外，应当理解，虽然本说明书按照实施方式加以描述，但并非每个实施方式仅包含一个独立的技术方案，说明书的这种叙述方式仅仅是为清楚起见，本领域技术人员应当将说明书作为一个整体，各实施例中的技术方案也可以经适当组合，形成本领域技术人员可以理解的其他实施方式。In addition, it should be understood that although this specification is described according to implementation modes, not each implementation mode only contains an independent technical solution, and this description in the specification is only for clarity, and those skilled in the art should take the specification as a whole , the technical solutions in the various embodiments can also be properly combined to form other implementations that can be understood by those skilled in the art.
Claims (1)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510250554.1A CN104809245A (en) | 2015-05-13 | 2015-05-13 | Image retrieval method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510250554.1A CN104809245A (en) | 2015-05-13 | 2015-05-13 | Image retrieval method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104809245A true CN104809245A (en) | 2015-07-29 |
Family
ID=53694067
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510250554.1A Pending CN104809245A (en) | 2015-05-13 | 2015-05-13 | Image retrieval method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104809245A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105760842A (en) * | 2016-02-26 | 2016-07-13 | 北京大学 | Station caption identification method based on combination of edge and texture features |
| CN106326902A (en) * | 2016-08-30 | 2017-01-11 | 刘广海 | Image retrieval method based on significance structure histogram |
| CN107193816A (en) * | 2016-03-14 | 2017-09-22 | 杭州华为企业通信技术有限公司 | A kind of image search method, virtual portrait image acquiring method and device |
| CN108121767A (en) * | 2017-11-28 | 2018-06-05 | 苏州市东皓计算机系统工程有限公司 | A kind of image search method of computer |
| CN108170711A (en) * | 2017-11-28 | 2018-06-15 | 苏州市东皓计算机系统工程有限公司 | A kind of image indexing system of computer |
| CN108875759A (en) * | 2017-05-10 | 2018-11-23 | 华为技术有限公司 | A kind of image processing method, device and server |
| CN109416313A (en) * | 2016-06-24 | 2019-03-01 | 拜克门寇尔特公司 | Image atlas system and method |
| CN112233025A (en) * | 2020-09-28 | 2021-01-15 | 杭州拼便宜网络科技有限公司 | Method, apparatus and readable storage medium for enhancing image recognizability |
| CN114898128A (en) * | 2022-04-21 | 2022-08-12 | 东声(苏州)智能科技有限公司 | Image similarity comparison method, storage medium and computer |
| CN119961480A (en) * | 2025-04-10 | 2025-05-09 | 微企（天津）信息技术有限公司 | A fast image retrieval method based on similarity |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6594386B1 (en) * | 1999-04-22 | 2003-07-15 | Forouzan Golshani | Method for computerized indexing and retrieval of digital images based on spatial color distribution |
| CN101551823A (en) * | 2009-04-20 | 2009-10-07 | 浙江师范大学 | Comprehensive multi-feature image retrieval method |
| CN102663391A (en) * | 2012-02-27 | 2012-09-12 | 安科智慧城市技术（中国）有限公司 | Image multifeature extraction and fusion method and system |
| CN103106265A (en) * | 2013-01-30 | 2013-05-15 | 北京工商大学 | Method and system of classifying similar images |
| CN104462481A (en) * | 2014-12-18 | 2015-03-25 | 浪潮(北京)电子信息产业有限公司 | Comprehensive image retrieval method based on colors and shapes |
| CN104572971A (en) * | 2014-12-31 | 2015-04-29 | 安科智慧城市技术（中国）有限公司 | Image retrieval method and device |
-
2015
- 2015-05-13 CN CN201510250554.1A patent/CN104809245A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6594386B1 (en) * | 1999-04-22 | 2003-07-15 | Forouzan Golshani | Method for computerized indexing and retrieval of digital images based on spatial color distribution |
| CN101551823A (en) * | 2009-04-20 | 2009-10-07 | 浙江师范大学 | Comprehensive multi-feature image retrieval method |
| CN102663391A (en) * | 2012-02-27 | 2012-09-12 | 安科智慧城市技术（中国）有限公司 | Image multifeature extraction and fusion method and system |
| CN103106265A (en) * | 2013-01-30 | 2013-05-15 | 北京工商大学 | Method and system of classifying similar images |
| CN104462481A (en) * | 2014-12-18 | 2015-03-25 | 浪潮(北京)电子信息产业有限公司 | Comprehensive image retrieval method based on colors and shapes |
| CN104572971A (en) * | 2014-12-31 | 2015-04-29 | 安科智慧城市技术（中国）有限公司 | Image retrieval method and device |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105760842A (en) * | 2016-02-26 | 2016-07-13 | 北京大学 | Station caption identification method based on combination of edge and texture features |
| CN107193816A (en) * | 2016-03-14 | 2017-09-22 | 杭州华为企业通信技术有限公司 | A kind of image search method, virtual portrait image acquiring method and device |
| CN109416313A (en) * | 2016-06-24 | 2019-03-01 | 拜克门寇尔特公司 | Image atlas system and method |
| US11448583B2 (en) | 2016-06-24 | 2022-09-20 | Beckman Coulter, Inc. | Image atlas systems and methods |
| CN106326902A (en) * | 2016-08-30 | 2017-01-11 | 刘广海 | Image retrieval method based on significance structure histogram |
| CN106326902B (en) * | 2016-08-30 | 2019-05-14 | 广西师范大学 | Image search method based on conspicuousness structure histogram |
| CN108875759B (en) * | 2017-05-10 | 2022-05-24 | 华为技术有限公司 | Image processing method and device and server |
| CN108875759A (en) * | 2017-05-10 | 2018-11-23 | 华为技术有限公司 | A kind of image processing method, device and server |
| CN108170711A (en) * | 2017-11-28 | 2018-06-15 | 苏州市东皓计算机系统工程有限公司 | A kind of image indexing system of computer |
| CN108121767A (en) * | 2017-11-28 | 2018-06-05 | 苏州市东皓计算机系统工程有限公司 | A kind of image search method of computer |
| CN112233025A (en) * | 2020-09-28 | 2021-01-15 | 杭州拼便宜网络科技有限公司 | Method, apparatus and readable storage medium for enhancing image recognizability |
| CN114898128A (en) * | 2022-04-21 | 2022-08-12 | 东声(苏州)智能科技有限公司 | Image similarity comparison method, storage medium and computer |
| CN119961480A (en) * | 2025-04-10 | 2025-05-09 | 微企（天津）信息技术有限公司 | A fast image retrieval method based on similarity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104809245A (en) | Image retrieval method | |
| CN102903128B (en) | The video image content editor's transmission method kept based on Similarity of Local Characteristic Structure | |
| CN107123088B (en) | A method for automatically changing the background color of a certificate photo | |
| Rathore et al. | Colour based image segmentation using L* a* b* colour space based on genetic algorithm | |
| CN106952271A (en) | A kind of image partition method handled based on super-pixel segmentation and EM/MPM | |
| CN110619648B (en) | Method for dividing image area based on RGB change trend | |
| CN104657980A (en) | Improved multi-channel image partitioning algorithm based on Meanshift | |
| CN102254326A (en) | Image segmentation method by using nucleus transmission | |
| CN111210447B (en) | A method and terminal for hierarchical segmentation of hematoxylin-eosin stained pathological images | |
| CN101930461A (en) | Digital image visualized management and retrieval for communication network | |
| CN103617596A (en) | Image color style transformation method based on flow pattern transition | |
| CN104504722A (en) | Method for correcting image colors through gray points | |
| CN107945200A (en) | Image binaryzation dividing method | |
| CN110084782A (en) | Full reference image quality appraisement method based on saliency detection | |
| CN103971367B (en) | Hydrologic data image segmenting method | |
| CN108154157A (en) | It is a kind of based on integrated quick Spectral Clustering | |
| CN103971134A (en) | Image classifying, retrieving and correcting method and corresponding device | |
| CN109345601A (en) | A method for color standardization of pathological images based on low-rank embedded non-negative matrix factorization | |
| CN107818341A (en) | A kind of color extraction method based on improvement K means algorithms | |
| Fernando et al. | Color features for dating historical color images | |
| CN103325101B (en) | The extracting method of color property and device | |
| CN110751660B (en) | Color image segmentation method | |
| Salih et al. | Adaptive local exposure based region determination for non-uniform illumination and low contrast images | |
| CN106127144A (en) | The point source risk source extraction method of spectrum empty integral feature model during employing | |
| Zhu et al. | Atmospheric light estimation in hazy images based on color-plane model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150729 |