2015 International Conference on Signal Processing and Communication Engineering Systems, 2015
In this paper, we developed an application that can be used to monitor network packets, bandwidth... more In this paper, we developed an application that can be used to monitor network packets, bandwidth, Protocol Packets from the network and easily can monitor the system networking performance. The system uses automated software engineering approach, especially unit test in Java. The system can be used for monitoring the TCP, UDP, ARP, packets, when the system is connected with the internet. Domain IP address can be detected and packet that is lost can also be measured. The packet is captured with JPcap and WinPcap tool, integrated in JVM. Testing of this software involves developing set of test cases that are similar to the real data that the NMT is intended to manipulate. This project is a prototype of software engineering methodology and software is successfully tested.
Face can be considered as multidimensional visual stimuli. Eunuchs are the special kind of human ... more Face can be considered as multidimensional visual stimuli. Eunuchs are the special kind of human being regarding the gender and their faces are also different in nature since these faces do not belong to either male or female gender. In this paper, a modified Local Binary Pattern (LBP) technique is used for extracting feature of eunuch faces and neural network based algorithm is used for face recognition. Recognition is done by Multilayer Feed Forward Neural Network with back proapgation learning rule. Here real life face images of the eunuchs are taken from North East India people and performance evaluation metrics like acceptance ratio and execution time are calculated.
Iris pattern matching is accepted worldwide as an efficient way of a personal identification and ... more Iris pattern matching is accepted worldwide as an efficient way of a personal identification and recognition by analyzing different patterns which are statistically unique [1–2, 10]. In this paper presented a large number of data set attributes are selected based on certain geometrical features such as shape, size, length and breadth. The geometrical features represented a vector to describe the cuttlefish object for identification and recognition in a meaningful manner. The classifier distinguishes the patterns based on the feature vector and performs classification or clustering that can be performed to recognize the cuttlefish eye.
It has been observed that there are certain species among various human races, various species of... more It has been observed that there are certain species among various human races, various species of animals and birds have iris pattern geometry which can’t be approximated by a circular shape, especially for the external boundary of the irises and pupils. The well-established Daugmans methods is mainly based on the assumption that the iris patterns basically consist of two circles in which inner one is non-concentric to the outer one .In the present study the existing 2D spatial filter has been transformed into a fully Cartesian coordinate system with the assumption that the iris patterns have almost square shaped except at the corners and pupils are non-circular in shape.
Handwritten text recognition is one of the toughest jobs for a computer system as handwriting doe... more Handwritten text recognition is one of the toughest jobs for a computer system as handwriting does not follow any uniform rules. Recognition of handwriting with greater accuracy is a very difficult task for the researcher. Researchers have done many experiments on the offline handwriting of different script, whereas research work on recognition of online character, word or documents for online handwritten data is quite less. Several offline and few online explorations have been done in recognition of English language but online character and word recognition of Indian language particularly for Bengali is an on-going and exciting research area as the alphabets of Bengali script is comparatively complicated than English in shape. A handwriting recognition system involves many pre-processing steps, after pre-processing step normalization is the most momentous step which is usually done before recognition. As different people write handwritten text in different style, so shapes of every...
Face can be considered as multidimensional visual stimuli. Eunuchs are the special kind of human ... more Face can be considered as multidimensional visual stimuli. Eunuchs are the special kind of human being regarding the gender and their faces are also different in nature since these faces do not belong to either male or female gender. In this paper, a modified Local Binary Pattern (LBP) technique is used for extracting feature of eunuch faces and neural network based algorithm is used for face recognition. Recognition is done by Multilayer Feed Forward Neural Network with back proapgation learning rule. Here real life face images of the eunuchs are taken from North East India people and performance evaluation metrics like acceptance ratio and execution time are calculated.
Journal of Ambient Intelligence and Humanized Computing, 2021
Dense fog is a vital cause of risk in driving perception, especially on a hilly road. In hilly ar... more Dense fog is a vital cause of risk in driving perception, especially on a hilly road. In hilly areas, drivers are unable to view the roads prominently and sometimes unable to notice a nearby object properly due to dense fog. The dense fog causes many road accidents and also reduces the speed of the vehicle. In this article, a vision-based real-time fast fog removal approach is proposed to obtain a prominent view of the hilly road during heavy fog by video processing techniques. The proposed approach is established on an atmospheric based scattering model and least filtering technique with a dynamic patch followed by independent histogram equalization built on color channels. First, the atmospheric light is estimated at an interval of 6000 frames using the least filtering technique with a dynamic patch. Then, frames are inverted to estimate the transmission map, and fog-free scenes are recovered. Finally, the independent histogram equalization based on color channel is used to elimin...
The vision problem of drivers during the night is mainly owing to the high-intensity headlight-be... more The vision problem of drivers during the night is mainly owing to the high-intensity headlight-beam of the oncoming vehicle from the reverse direction. It causes temporary blindness to the driver. To overcome this situation, people generally use color windshield glass, sun visor, and night-vision glass. But, these are not considered as the best solution since it decreases the light intensity of the entire view including the road. Many researchers used various image enhancement techniques to overcome this situation. But, the existing approaches are unable to dim the high-beam headlights of oncoming vehicles without affecting the road view. In this paper, a novel night-vision system is proposed to resolve the problem in real-time for manual-driving vehicles and autonomous vehicles. The proposed method includes region segmentation of frames, local enhancement techniques in different regions followed by adaptive Gaussian filtering. Pixels masking, gamma correction, and low-light pixel enhancement are applied to three distinct regions. Both autonomous vehicles and manual drivers can get a bright and a prominent view of the road with dim headlights of oncoming vehicles in real-time. Numerous heuristic real-time test reveals the performance superiority of the projected system compared to state-of-art methods in quantitative as well as qualitative point of view.
The Iris pattern of any animal (including human being) is statistically unique and suitable for b... more The Iris pattern of any animal (including human being) is statistically unique and suitable for biometric measurements. The identity of the animal concerned can be determined and verified comparing the templates obtained with the present algorithm with that template stored in database which was formed on the basis of previous studies. In the present study, the method of circular Hough transform is used for segmentation of the tiger Iris and subsequently Daugman‘s rubber Sheet model is used for normalization of the segmented values. Pattern matching is achieved by calculating Hamming Distance where its degree is proportional to the closeness of matching. The closer matching between the stored and calculated pattern is found to lead towards better recognition of Irises and thereby the animal itself.
2015 International Conference on Signal Processing and Communication Engineering Systems, 2015
In this paper, we developed an application that can be used to monitor network packets, bandwidth... more In this paper, we developed an application that can be used to monitor network packets, bandwidth, Protocol Packets from the network and easily can monitor the system networking performance. The system uses automated software engineering approach, especially unit test in Java. The system can be used for monitoring the TCP, UDP, ARP, packets, when the system is connected with the internet. Domain IP address can be detected and packet that is lost can also be measured. The packet is captured with JPcap and WinPcap tool, integrated in JVM. Testing of this software involves developing set of test cases that are similar to the real data that the NMT is intended to manipulate. This project is a prototype of software engineering methodology and software is successfully tested.
Face can be considered as multidimensional visual stimuli. Eunuchs are the special kind of human ... more Face can be considered as multidimensional visual stimuli. Eunuchs are the special kind of human being regarding the gender and their faces are also different in nature since these faces do not belong to either male or female gender. In this paper, a modified Local Binary Pattern (LBP) technique is used for extracting feature of eunuch faces and neural network based algorithm is used for face recognition. Recognition is done by Multilayer Feed Forward Neural Network with back proapgation learning rule. Here real life face images of the eunuchs are taken from North East India people and performance evaluation metrics like acceptance ratio and execution time are calculated.
Iris pattern matching is accepted worldwide as an efficient way of a personal identification and ... more Iris pattern matching is accepted worldwide as an efficient way of a personal identification and recognition by analyzing different patterns which are statistically unique [1–2, 10]. In this paper presented a large number of data set attributes are selected based on certain geometrical features such as shape, size, length and breadth. The geometrical features represented a vector to describe the cuttlefish object for identification and recognition in a meaningful manner. The classifier distinguishes the patterns based on the feature vector and performs classification or clustering that can be performed to recognize the cuttlefish eye.
It has been observed that there are certain species among various human races, various species of... more It has been observed that there are certain species among various human races, various species of animals and birds have iris pattern geometry which can’t be approximated by a circular shape, especially for the external boundary of the irises and pupils. The well-established Daugmans methods is mainly based on the assumption that the iris patterns basically consist of two circles in which inner one is non-concentric to the outer one .In the present study the existing 2D spatial filter has been transformed into a fully Cartesian coordinate system with the assumption that the iris patterns have almost square shaped except at the corners and pupils are non-circular in shape.
Handwritten text recognition is one of the toughest jobs for a computer system as handwriting doe... more Handwritten text recognition is one of the toughest jobs for a computer system as handwriting does not follow any uniform rules. Recognition of handwriting with greater accuracy is a very difficult task for the researcher. Researchers have done many experiments on the offline handwriting of different script, whereas research work on recognition of online character, word or documents for online handwritten data is quite less. Several offline and few online explorations have been done in recognition of English language but online character and word recognition of Indian language particularly for Bengali is an on-going and exciting research area as the alphabets of Bengali script is comparatively complicated than English in shape. A handwriting recognition system involves many pre-processing steps, after pre-processing step normalization is the most momentous step which is usually done before recognition. As different people write handwritten text in different style, so shapes of every...
Face can be considered as multidimensional visual stimuli. Eunuchs are the special kind of human ... more Face can be considered as multidimensional visual stimuli. Eunuchs are the special kind of human being regarding the gender and their faces are also different in nature since these faces do not belong to either male or female gender. In this paper, a modified Local Binary Pattern (LBP) technique is used for extracting feature of eunuch faces and neural network based algorithm is used for face recognition. Recognition is done by Multilayer Feed Forward Neural Network with back proapgation learning rule. Here real life face images of the eunuchs are taken from North East India people and performance evaluation metrics like acceptance ratio and execution time are calculated.
Journal of Ambient Intelligence and Humanized Computing, 2021
Dense fog is a vital cause of risk in driving perception, especially on a hilly road. In hilly ar... more Dense fog is a vital cause of risk in driving perception, especially on a hilly road. In hilly areas, drivers are unable to view the roads prominently and sometimes unable to notice a nearby object properly due to dense fog. The dense fog causes many road accidents and also reduces the speed of the vehicle. In this article, a vision-based real-time fast fog removal approach is proposed to obtain a prominent view of the hilly road during heavy fog by video processing techniques. The proposed approach is established on an atmospheric based scattering model and least filtering technique with a dynamic patch followed by independent histogram equalization built on color channels. First, the atmospheric light is estimated at an interval of 6000 frames using the least filtering technique with a dynamic patch. Then, frames are inverted to estimate the transmission map, and fog-free scenes are recovered. Finally, the independent histogram equalization based on color channel is used to elimin...
The vision problem of drivers during the night is mainly owing to the high-intensity headlight-be... more The vision problem of drivers during the night is mainly owing to the high-intensity headlight-beam of the oncoming vehicle from the reverse direction. It causes temporary blindness to the driver. To overcome this situation, people generally use color windshield glass, sun visor, and night-vision glass. But, these are not considered as the best solution since it decreases the light intensity of the entire view including the road. Many researchers used various image enhancement techniques to overcome this situation. But, the existing approaches are unable to dim the high-beam headlights of oncoming vehicles without affecting the road view. In this paper, a novel night-vision system is proposed to resolve the problem in real-time for manual-driving vehicles and autonomous vehicles. The proposed method includes region segmentation of frames, local enhancement techniques in different regions followed by adaptive Gaussian filtering. Pixels masking, gamma correction, and low-light pixel enhancement are applied to three distinct regions. Both autonomous vehicles and manual drivers can get a bright and a prominent view of the road with dim headlights of oncoming vehicles in real-time. Numerous heuristic real-time test reveals the performance superiority of the projected system compared to state-of-art methods in quantitative as well as qualitative point of view.
The Iris pattern of any animal (including human being) is statistically unique and suitable for b... more The Iris pattern of any animal (including human being) is statistically unique and suitable for biometric measurements. The identity of the animal concerned can be determined and verified comparing the templates obtained with the present algorithm with that template stored in database which was formed on the basis of previous studies. In the present study, the method of circular Hough transform is used for segmentation of the tiger Iris and subsequently Daugman‘s rubber Sheet model is used for normalization of the segmented values. Pattern matching is achieved by calculating Hamming Distance where its degree is proportional to the closeness of matching. The closer matching between the stored and calculated pattern is found to lead towards better recognition of Irises and thereby the animal itself.
Uploads
Papers