International Journal of Integrated Engineering, 2021
Keratoconus (KC) is a condition of the bulging of the eye cornea. It is a common non-inflammatory... more Keratoconus (KC) is a condition of the bulging of the eye cornea. It is a common non-inflammatory ocular disorder that affects mostly the younger populace below the age of 30. The eye cornea bulges because of the conical displacement of either outwards or downwards. Such condition can greatly reduce one’s visual ability. Therefore, in this paper, we afford a mobile solution to mitigate the KC disorder using the state-of-the-art deep transfer learning method. We intend to use the pre-trained VGGNet-16 model and a conventional convolutional neural network to detect KC automatically. The experimental work uses a total of 4000 side view lateral segment photographed images (LSPIs) comprising 2000 of KC and non-KC or healthy each involving 125 subjects. The LSPIs were extracted from the video data captured using a smartphone. Fine tuning of three hyperparameters namely the learning rate (LR), batch size (BS) and epoch number (EN) were carried out during the training phase to generate the ...
2020 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), 2021
Studies have shown some correlations between retinal vessel morphologies and multiple systemic di... more Studies have shown some correlations between retinal vessel morphologies and multiple systemic diseases. While this could pave the way to timely diagnosis of such diseases by examining vessels from fundus images, practical application of measuring and quantifying changes in vessel width over time remains a challenge. In this study, we propose a semi-automated estimation method to efficiently summarize vessel width characteristics from fundus images. The method consists of retinal vessel segmentation, optic disc (OD) localization and vessel width parameters estimation. The proposed method is validated using a public database of high-resolution fundus images called HRF, where the significance of obtained vessel width parameters in differentiating the three image groups in the database are analysed. Results indicate that the obtained parameter using the method that summarises the ratio between width of veins to arteries, AVR (Artery-Vein Ratio) can be used to differentiate images from patients with Diabetic Retinopathy against healthy and glaucomatous patients.
2017 6th International Conference on Electrical Engineering and Informatics (ICEEI), 2017
Image retrieval system (IRS) is a searching system that uses certain characteristics or context i... more Image retrieval system (IRS) is a searching system that uses certain characteristics or context in an image. In the medical field, the IRS has been used to provide the needed correct images to the physicians while the diagnosis and treatment process is being conducted. In this paper, the research focus is on content-based IRS. In content-based IRS, two phases are discussed: feature extraction and selection, and the retrieval phase. The feature extraction technique is based on global shape descriptor (GSD), Hu moment invariant (Hu) and Fourier descriptor (FD) while the feature selection technique uses analysis of variance (ANOVA). The retrieval phase is implemented with the new feature vector formed and the performance is evaluated using four distance metrics namely Euclidean (E), Manhattan (M), Normalized Euclidean (NE) and Normalized Manhattan (NM). The experiment for CBIRS is performed on 100 MRI human spine images for each thoracic, lumbar and sacrum. The retrieval performances gave the best result for NM in retrieving the lumbar bones which the precision is up to 91.1%.
Journal of Telecommunication, Electronic and Computer Engineering, 2016
Research in iris recognition has been explosive in recent years. There are a few fundamental issu... more Research in iris recognition has been explosive in recent years. There are a few fundamental issues in iris recognition such as iris acquisition, iris segmentation, texture analysis and matching analysis that has been brought up. In this paper, we focus on a fundamental issue in iris segmentation which is segmentation accuracy. The accuracy of iris segmentation can be negatively affected because of poor segmentation of iris boundary. Iris boundary might have unsmooth, poor and unclear edges. Because of that, a method that can segment this type of boundary needs to be developed. A method based on active contour is proposed not only to increase the segmentation accuracy, but also to increase the recognition accuracy. The proposed method is compared with the modified Hough Transform method to observe the performance of both methods. Iris images from CASIA v4 are used for our experiment. According to results, the proposed method is better than the modified Hough Transform method in term...
Journal of Telecommunication, Electronic and Computer Engineering, 2016
Iris recognition is a biometric system that uses human iris features to determine and verify the ... more Iris recognition is a biometric system that uses human iris features to determine and verify the identity of human. Other biometric systems are fingerprint, face, ear, voice, gait, blood vessels and many more. A complete iris recognition system includes: iris acquisition, iris segmentation, feature extraction and matching. The main factor to obtain high segmentation and recognition accuracy is the quality of iris pattern. The quality of iris pattern can be affected because of specular reflection. Specular reflection happens during iris acquisition and it can reduce the features of iris pattern. This work is significant since the improved iris pattern can enhance the performance of iris localization, iris segmentation and feature extraction in the iris recognition system. In this paper, the iris image enhancement methods are proposed to remove the specular reflection. UBIRIS v1 and CASIA v4 databases are used for testing. Based on the results, the proposed methods managed to remove t...
Segmentation, where pixels are categorized by tissue types, is essential in medical image process... more Segmentation, where pixels are categorized by tissue types, is essential in medical image processing. This paper proposes a multi-level Fuzzy C-Means method to extract an intracranial from its background and skull. Then, a two-level Otsu multi-thresholding method is applied to segment the intracranial structure into cerebrospinal fluid, brain matters and other homogenous regions. Based on symmetrical properties in the intracranial
Journal of Computational Information Systems, 2012
Colour constancy concerns about the transformation of input image into a canonical form. We appro... more Colour constancy concerns about the transformation of input image into a canonical form. We approach the constancy issue by applying masked grey world algorithm to the SURF detector. The aim is to produce a robust feature detector that is invariant to sudden as well as gradual illumination change. We have analyzed the algorithm with various types of object surfaces, including minimal, dielectric, metallic specularity and fluorescent surface. The results show that regardless of the surface type, masked grey world have improved ...
Keratoconus (KC) is a common noninflammatory ocular disorder affecting mostly the younger generat... more Keratoconus (KC) is a common noninflammatory ocular disorder affecting mostly the younger generation of age 30 and below. Typically, KC patients will have symptoms of bulging eye cornea resulting from the conical displacement either heading outwards or downwards. This condition is a serious matter since it can affect the affected person's visual ability. As such, this paper intends to describe the developmental work involving the use of the pre-trained VGGNet-16 model and a conventional convolutional neural network to detect KC automatically. This experiment uses a total of 2000 KC, and 2000 healthy lateral segment photographed images (LSPI) extracted from videos captured from the side view of 125 patients using a smartphone camera. Three hyperparameters are fine-tuned during the training phase to generate the best model. From the results, we observe that the VGGNet-16 model with a learning rate of 0.0001, batch size of 16, and the epoch number of 70 is the best model. The propo...
Bulletin of Electrical Engineering and Informatics
Iris recognition used the iris features to verify and identify the identity of human. The iris ha... more Iris recognition used the iris features to verify and identify the identity of human. The iris has many advantages such as stability over time, easy to use and high recognition accuracy. However, the poor quality of iris images can degrade the recognition accuracy of iris recognition system. The recognition accuracy of this system is depended on the iris pattern quality captured during the iris acquisition. The iris pattern quality can degrade due to the blurry image. Blurry image happened due to the movement during image acquisition and poor camera resolution. Due to that, a deblurring method based on the Wiener filter was proposed to improve the quality of iris pattern. This work is significant since the proposed method can enhance the quality of iris pattern in the blurry image. Based to the results, the proposed method improved the quality of iris pattern in the blurry image. Moreover, it recorded the fastest execution time to improve the quality of iris pattern compared to the ...
Bulletin of Electrical Engineering and Informatics
Iris recognition has been around for many years due to an extensive research on the uniqueness of... more Iris recognition has been around for many years due to an extensive research on the uniqueness of human iris. It is well known that the iris is not similar to each other which means every human in the planet has their own iris pattern and cannot be shared. One of the main issues in iris recognition is iris segmentation. One element that can reduce the accuracy of iris segmentation is the presence of specular reflection. Another issue is the speed of specular reflection removal since the iris recognition system needs to process a lot of irises. In this paper, a specular reflection removal method was proposed to achieve a fast and accurate specular reflection removal. Some modifications were implemented on the existing pixels properties method. Based on the results, the proposed method achieved the fastest execution time, the highest segmentation accuracy and the highest SSIM compared to the other methods. This proves that the proposed method is fast and accurate to be implemented in ...
Over recent years, iris recognition has been an explosive growth of interest in human identificat... more Over recent years, iris recognition has been an explosive growth of interest in human identification due to its high accuracy. Iris recognition is a biometric system that uses iris to verify and identify human identity. Iris has pattern that is rich with textures and can be compared among humans. There are many methods can be used in iris recognition. The methods based on the integro-differential operator and Hough transform are the most widely used in iris recognition. Unfortunately, both methods require more time to execute and has less accurate recognition accuracy due to the eyelid occlusion. In order to solve these problems, the Chan-Vese active contour is modified to reduce the execution time and to increase the recognition accuracy of iris recognition. Then, this method is compared with the integro-differential operator method. The iris images from CASIA-v4 database are used for the experiments. According to the results, the proposed method recorded 0.91 s for execution time ...
This work presents a qualitative measurement of anterior segment photographed images (ASPIs) to i... more This work presents a qualitative measurement of anterior segment photographed images (ASPIs) to identify between normal eyes and eyes with pterygium and pinguecula through Otsu multi-thresholding approach without contrast enhancement. In addition, we also propose a mobile screening framework of ASPIs through smartphones. ASPIs were directly sent to the cloud storage once an ASPI was captured using a smartphone camera, and then each image was processed through a digital image processing approach in a processing platform. Three important steps, namely, pre-processing, image segmentation and qualitative assessment, are involved in the processing platform of the mobile screening framework. The ASPIs are pre-processed to minimise or eliminate any unwanted areas within the image. Then, these ASPIs are segmented through multi-thresholding Otsu approach with clustering number n = 3. Segmentation result shows that the accuracy of the proposed method is 87.5%, which is comparable with the pre...
In current clinical practice, there is no specific standard and grading system that can be used t... more In current clinical practice, there is no specific standard and grading system that can be used to measure the behaviour of the retinal blood vessel curvature. The retinal blood vessel curvature is measured based on clinical experiences. It is very subjective and inconsistent to describe the presence of tortuosity in fundus images. Thus, this paper aims to measure the tortuosity of retinal blood vessel using curvature-based method and investigate its relationship with diabetic retinopathy (DR) disease. The proposed tortuosity measures have been tested on 43 fundus images belonging to patients who have been diagnosed with DR disease and validated by two clinical experts from our collaborative hospital. On average, the proposed algorithm achieved 90.7% (accuracy), 98.72% (sensitivity) and 9.3% (false negative rate), that shows significant tortuosity presence in diabetic retinopathy fundus images.
International Journal of Integrated Engineering, 2021
Keratoconus (KC) is a condition of the bulging of the eye cornea. It is a common non-inflammatory... more Keratoconus (KC) is a condition of the bulging of the eye cornea. It is a common non-inflammatory ocular disorder that affects mostly the younger populace below the age of 30. The eye cornea bulges because of the conical displacement of either outwards or downwards. Such condition can greatly reduce one’s visual ability. Therefore, in this paper, we afford a mobile solution to mitigate the KC disorder using the state-of-the-art deep transfer learning method. We intend to use the pre-trained VGGNet-16 model and a conventional convolutional neural network to detect KC automatically. The experimental work uses a total of 4000 side view lateral segment photographed images (LSPIs) comprising 2000 of KC and non-KC or healthy each involving 125 subjects. The LSPIs were extracted from the video data captured using a smartphone. Fine tuning of three hyperparameters namely the learning rate (LR), batch size (BS) and epoch number (EN) were carried out during the training phase to generate the ...
2020 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), 2021
Studies have shown some correlations between retinal vessel morphologies and multiple systemic di... more Studies have shown some correlations between retinal vessel morphologies and multiple systemic diseases. While this could pave the way to timely diagnosis of such diseases by examining vessels from fundus images, practical application of measuring and quantifying changes in vessel width over time remains a challenge. In this study, we propose a semi-automated estimation method to efficiently summarize vessel width characteristics from fundus images. The method consists of retinal vessel segmentation, optic disc (OD) localization and vessel width parameters estimation. The proposed method is validated using a public database of high-resolution fundus images called HRF, where the significance of obtained vessel width parameters in differentiating the three image groups in the database are analysed. Results indicate that the obtained parameter using the method that summarises the ratio between width of veins to arteries, AVR (Artery-Vein Ratio) can be used to differentiate images from patients with Diabetic Retinopathy against healthy and glaucomatous patients.
2017 6th International Conference on Electrical Engineering and Informatics (ICEEI), 2017
Image retrieval system (IRS) is a searching system that uses certain characteristics or context i... more Image retrieval system (IRS) is a searching system that uses certain characteristics or context in an image. In the medical field, the IRS has been used to provide the needed correct images to the physicians while the diagnosis and treatment process is being conducted. In this paper, the research focus is on content-based IRS. In content-based IRS, two phases are discussed: feature extraction and selection, and the retrieval phase. The feature extraction technique is based on global shape descriptor (GSD), Hu moment invariant (Hu) and Fourier descriptor (FD) while the feature selection technique uses analysis of variance (ANOVA). The retrieval phase is implemented with the new feature vector formed and the performance is evaluated using four distance metrics namely Euclidean (E), Manhattan (M), Normalized Euclidean (NE) and Normalized Manhattan (NM). The experiment for CBIRS is performed on 100 MRI human spine images for each thoracic, lumbar and sacrum. The retrieval performances gave the best result for NM in retrieving the lumbar bones which the precision is up to 91.1%.
Journal of Telecommunication, Electronic and Computer Engineering, 2016
Research in iris recognition has been explosive in recent years. There are a few fundamental issu... more Research in iris recognition has been explosive in recent years. There are a few fundamental issues in iris recognition such as iris acquisition, iris segmentation, texture analysis and matching analysis that has been brought up. In this paper, we focus on a fundamental issue in iris segmentation which is segmentation accuracy. The accuracy of iris segmentation can be negatively affected because of poor segmentation of iris boundary. Iris boundary might have unsmooth, poor and unclear edges. Because of that, a method that can segment this type of boundary needs to be developed. A method based on active contour is proposed not only to increase the segmentation accuracy, but also to increase the recognition accuracy. The proposed method is compared with the modified Hough Transform method to observe the performance of both methods. Iris images from CASIA v4 are used for our experiment. According to results, the proposed method is better than the modified Hough Transform method in term...
Journal of Telecommunication, Electronic and Computer Engineering, 2016
Iris recognition is a biometric system that uses human iris features to determine and verify the ... more Iris recognition is a biometric system that uses human iris features to determine and verify the identity of human. Other biometric systems are fingerprint, face, ear, voice, gait, blood vessels and many more. A complete iris recognition system includes: iris acquisition, iris segmentation, feature extraction and matching. The main factor to obtain high segmentation and recognition accuracy is the quality of iris pattern. The quality of iris pattern can be affected because of specular reflection. Specular reflection happens during iris acquisition and it can reduce the features of iris pattern. This work is significant since the improved iris pattern can enhance the performance of iris localization, iris segmentation and feature extraction in the iris recognition system. In this paper, the iris image enhancement methods are proposed to remove the specular reflection. UBIRIS v1 and CASIA v4 databases are used for testing. Based on the results, the proposed methods managed to remove t...
Segmentation, where pixels are categorized by tissue types, is essential in medical image process... more Segmentation, where pixels are categorized by tissue types, is essential in medical image processing. This paper proposes a multi-level Fuzzy C-Means method to extract an intracranial from its background and skull. Then, a two-level Otsu multi-thresholding method is applied to segment the intracranial structure into cerebrospinal fluid, brain matters and other homogenous regions. Based on symmetrical properties in the intracranial
Journal of Computational Information Systems, 2012
Colour constancy concerns about the transformation of input image into a canonical form. We appro... more Colour constancy concerns about the transformation of input image into a canonical form. We approach the constancy issue by applying masked grey world algorithm to the SURF detector. The aim is to produce a robust feature detector that is invariant to sudden as well as gradual illumination change. We have analyzed the algorithm with various types of object surfaces, including minimal, dielectric, metallic specularity and fluorescent surface. The results show that regardless of the surface type, masked grey world have improved ...
Keratoconus (KC) is a common noninflammatory ocular disorder affecting mostly the younger generat... more Keratoconus (KC) is a common noninflammatory ocular disorder affecting mostly the younger generation of age 30 and below. Typically, KC patients will have symptoms of bulging eye cornea resulting from the conical displacement either heading outwards or downwards. This condition is a serious matter since it can affect the affected person's visual ability. As such, this paper intends to describe the developmental work involving the use of the pre-trained VGGNet-16 model and a conventional convolutional neural network to detect KC automatically. This experiment uses a total of 2000 KC, and 2000 healthy lateral segment photographed images (LSPI) extracted from videos captured from the side view of 125 patients using a smartphone camera. Three hyperparameters are fine-tuned during the training phase to generate the best model. From the results, we observe that the VGGNet-16 model with a learning rate of 0.0001, batch size of 16, and the epoch number of 70 is the best model. The propo...
Bulletin of Electrical Engineering and Informatics
Iris recognition used the iris features to verify and identify the identity of human. The iris ha... more Iris recognition used the iris features to verify and identify the identity of human. The iris has many advantages such as stability over time, easy to use and high recognition accuracy. However, the poor quality of iris images can degrade the recognition accuracy of iris recognition system. The recognition accuracy of this system is depended on the iris pattern quality captured during the iris acquisition. The iris pattern quality can degrade due to the blurry image. Blurry image happened due to the movement during image acquisition and poor camera resolution. Due to that, a deblurring method based on the Wiener filter was proposed to improve the quality of iris pattern. This work is significant since the proposed method can enhance the quality of iris pattern in the blurry image. Based to the results, the proposed method improved the quality of iris pattern in the blurry image. Moreover, it recorded the fastest execution time to improve the quality of iris pattern compared to the ...
Bulletin of Electrical Engineering and Informatics
Iris recognition has been around for many years due to an extensive research on the uniqueness of... more Iris recognition has been around for many years due to an extensive research on the uniqueness of human iris. It is well known that the iris is not similar to each other which means every human in the planet has their own iris pattern and cannot be shared. One of the main issues in iris recognition is iris segmentation. One element that can reduce the accuracy of iris segmentation is the presence of specular reflection. Another issue is the speed of specular reflection removal since the iris recognition system needs to process a lot of irises. In this paper, a specular reflection removal method was proposed to achieve a fast and accurate specular reflection removal. Some modifications were implemented on the existing pixels properties method. Based on the results, the proposed method achieved the fastest execution time, the highest segmentation accuracy and the highest SSIM compared to the other methods. This proves that the proposed method is fast and accurate to be implemented in ...
Over recent years, iris recognition has been an explosive growth of interest in human identificat... more Over recent years, iris recognition has been an explosive growth of interest in human identification due to its high accuracy. Iris recognition is a biometric system that uses iris to verify and identify human identity. Iris has pattern that is rich with textures and can be compared among humans. There are many methods can be used in iris recognition. The methods based on the integro-differential operator and Hough transform are the most widely used in iris recognition. Unfortunately, both methods require more time to execute and has less accurate recognition accuracy due to the eyelid occlusion. In order to solve these problems, the Chan-Vese active contour is modified to reduce the execution time and to increase the recognition accuracy of iris recognition. Then, this method is compared with the integro-differential operator method. The iris images from CASIA-v4 database are used for the experiments. According to the results, the proposed method recorded 0.91 s for execution time ...
This work presents a qualitative measurement of anterior segment photographed images (ASPIs) to i... more This work presents a qualitative measurement of anterior segment photographed images (ASPIs) to identify between normal eyes and eyes with pterygium and pinguecula through Otsu multi-thresholding approach without contrast enhancement. In addition, we also propose a mobile screening framework of ASPIs through smartphones. ASPIs were directly sent to the cloud storage once an ASPI was captured using a smartphone camera, and then each image was processed through a digital image processing approach in a processing platform. Three important steps, namely, pre-processing, image segmentation and qualitative assessment, are involved in the processing platform of the mobile screening framework. The ASPIs are pre-processed to minimise or eliminate any unwanted areas within the image. Then, these ASPIs are segmented through multi-thresholding Otsu approach with clustering number n = 3. Segmentation result shows that the accuracy of the proposed method is 87.5%, which is comparable with the pre...
In current clinical practice, there is no specific standard and grading system that can be used t... more In current clinical practice, there is no specific standard and grading system that can be used to measure the behaviour of the retinal blood vessel curvature. The retinal blood vessel curvature is measured based on clinical experiences. It is very subjective and inconsistent to describe the presence of tortuosity in fundus images. Thus, this paper aims to measure the tortuosity of retinal blood vessel using curvature-based method and investigate its relationship with diabetic retinopathy (DR) disease. The proposed tortuosity measures have been tested on 43 fundus images belonging to patients who have been diagnosed with DR disease and validated by two clinical experts from our collaborative hospital. On average, the proposed algorithm achieved 90.7% (accuracy), 98.72% (sensitivity) and 9.3% (false negative rate), that shows significant tortuosity presence in diabetic retinopathy fundus images.
Uploads
Papers