Helping a disable subject for improving their quality of life and providing them a priorit care at the right time is one of the most important things for us a responsible member of researcher. Hence there is a need fo...
详细信息
Helping a disable subject for improving their quality of life and providing them a priorit care at the right time is one of the most important things for us a responsible member of researcher. Hence there is a need for developing a wheelchair that is intelligent, provides easy maneuverability, and safety to drive. A brain intelligent wheelchair, which uses the recorded signals from the brain and processes it to control the wheelchair has been designed. However, it has not yet been widely adopted, and any commercial device would need proper safety trials and approval before release. In this paper, a smart wheelchair based bio-signal & non bio-signal approach which translated into movement commands by the arduino microcontroller is proposed. Four ultrasonics sensor, a raspicam for obstacle detection, and Inertial Measurement Unit for speed controller on sloping road are integrated with the wheelchair based biosignals called brain-controlled wheelchair. The performance improvement of the of the obstacle avoidance are examinated. The evaluation of the wheelchair movement is performed under real conditions using direction and speed control commands of the wheelchair. It is obtained that the misclassification is reduced and the accuracy is increased.
Feature extraction is an essential step in many imageprocessing and computer vision applications. It is quite desirable that the extracted features can effectively represent an image. Furthermore, the dominant inform...
详细信息
ISBN:
(纸本)9788132225386;9788132225379
Feature extraction is an essential step in many imageprocessing and computer vision applications. It is quite desirable that the extracted features can effectively represent an image. Furthermore, the dominant information visually perceived by human beings should be efficiently represented by the extracted features. Over the last few decades, different algorithms are proposed to address the major issues of image representations by the efficient features. Gabor wavelet is one of the most widely used filters for image feature extraction. Existing Gabor wavelet-based feature extraction methodologies unnecessarily use both the real and the imaginary coefficients, which are subsequently processed by dimensionality reduction techniques such as PCA, LDA etc. This procedure ultimately affects the overall performance of the algorithm in terms of memory requirement and the computational complexity. To address this particular issue, we proposed a local image feature extraction method by using a Gabor wavelet. In our method, an image is divided into overlapping image blocks, and subsequently each of the image blocks are separately filtered out by Gabor wavelet. Finally, the extracted coefficients are concatenated to get the proposed local feature vector. The efficacy and effectiveness of the proposed feature extraction method is evaluated using the estimation of mean square error (MSE), peak signal-to-noise ratio (PSNR), and the correlation coefficient (CC) by reconstructing the original image using the extracted features, and compared it with the original input image. All these performance evaluation measures clearly show that real coefficients of the Gabor filter alone can effectively represent an image as compared to the methods which utilize either the imaginary coefficients or the both. The major novelty of our method lies on our claim-capability of the real coefficients of a Gabor filter for image representation.
Person identification based on biometrics is drawing more and more attentions in identity and information safety. This paper presents a biometric system to identify person using 3D palmprint data, including a non-cont...
详细信息
ISBN:
(数字)9781510604704
ISBN:
(纸本)9781510604698;9781510604704
Person identification based on biometrics is drawing more and more attentions in identity and information safety. This paper presents a biometric system to identify person using 3D palmprint data, including a non-contact system capturing 3D palmprint quickly and a method identifying 3D palmprint fast. In order to reduce the effect of slight shaking of palm on the data accuracy, a DLP (Digital Light processing) projector is utilized to trigger a CCD camera based on structured-light and triangulation measurement and 3D palmprint data could be gathered within 1 second. Using the obtained database and the PolyU 3D palmprint database, feature extraction and matching method is presented based on MCI (Mean Curvature image), Gabor filter and binary code list. Experimental results show that the proposed method can identify a person within 240 ms in the case of 4000 samples. Compared with the traditional 3D palmprint recognition methods, the proposed method has high accuracy, low EER (Equal Error Rate), small storage space, and fast identification speed.
In this paper, General Purpose Graphical processing Unit (GPGPU) based concurrent implementation of handwritten digit classifier is presented. Different styles of handwriting make it difficult to recognize a pattern b...
详细信息
ISBN:
(纸本)9781509055869
In this paper, General Purpose Graphical processing Unit (GPGPU) based concurrent implementation of handwritten digit classifier is presented. Different styles of handwriting make it difficult to recognize a pattern but using neural network, it is not a difficult task to perform. Different softwares like torch and MATLAB provide the support of multiple training algorithms to train a network. By choosing an appropriate training algorithm for a specific application, speed of training can be increased. Furthermore, using computational power of GPUs, training and classification speed of neural network can be significantly improved. In this work, Modified National Institute of Standards and Technology (MNIST) database of handwritten digits is used to train the network. Accuracy and training time of digit classifier is evaluated for different algorithms and then concurrent training is performed by exploiting power of GPU. Trained parameters are imported and used for the concurrent classification with Compute Unified Device Architecture (CUDA) computing language which can be useful in numerous practical applications. Finally, the results of sequential and concurrent operations of training and classification are compared.
This paper proposes an efficient algorithm for real-time traffic sign detection. The article considers the practicability of using HSV color space to extract the red color. An algorithm to remove noise to improve the ...
详细信息
ISBN:
(数字)9783319302225
ISBN:
(纸本)9783319302225;9783319302218
This paper proposes an efficient algorithm for real-time traffic sign detection. The article considers the practicability of using HSV color space to extract the red color. An algorithm to remove noise to improve the accuracy and speed of detection was developed. A modified Generalized Hough transform is then used to detect traffic signs. The current velocity of a vehicle is used to predict the sign's location in the adjacent frames in a video sequence. Finally, the detected objects are being classified. The detection and classification of road signs algorithms are implemented using CUDA and operate in real time on an Android device. The developed algorithms have been tested using real scene images and the German Traffic Sign Detection Benchmark (GTSDB) dataset and showed efficient results.
For many imageprocessing workflows, including change detection and data fusion, an accurate and automated image-To-image registration is a critical precondition. Particularly registering images with different modalit...
详细信息
A reconfigurable computing architecture based on Field Programmable Gate Array (FPGA) technology is implemented for the Electrical Capacitance Tomography (ECT) system. The ECT system is used to image the multi-phase f...
详细信息
ISBN:
(纸本)9781509034741
A reconfigurable computing architecture based on Field Programmable Gate Array (FPGA) technology is implemented for the Electrical Capacitance Tomography (ECT) system. The ECT system is used to image the multi-phase flow when gas/liquid or solid/liquid phases occurs. In the ECT systems, an exhaustive computational image reconstruction algorithm has to vastly processed large amount of data. The software algorithms and hardware parameters are adjusted based on a Hardware software codesign process using commercially available tools. The hardware system consists of capacitive sensors, wireless nodes and FPGA module. Rr4wesults show that implementing the ECT image reconstruction algorithm on the FPGA platform achives fast performance and small design density.
In surveillance systems a constant monitoring is required for high security purpose, however the videos or the images captured here can be degraded because of low illumination environment and foggy atmosphere. In this...
详细信息
In surveillance systems a constant monitoring is required for high security purpose, however the videos or the images captured here can be degraded because of low illumination environment and foggy atmosphere. In this paper we have developed a system that acquires images through motion detection and enhance the quality of image with illumination adjustment and haze removal algorithms in FPGA. The motion detection algorithm has been implemented in MATLAB r2013a whereas the acquired image has been processed in FPGA Virtex 6 ML605 evaluation board. The visual quality of the image cannot be judged merely by observing image but also by determining some parameters like PSNR, MSE etc. So on the basis of implementation results it has been observed that the illumination levels of the image has been adjusted and the haze has been removed to some extent and in addition to that the system requires less time for processing purpose.
Steganalysis is capable of identifying the carrier(s) which have information hidden in them in such a way that their very existence is concealed. In this paper we propose a classification system with neural networks w...
详细信息
ISBN:
(纸本)9781509010226
Steganalysis is capable of identifying the carrier(s) which have information hidden in them in such a way that their very existence is concealed. In this paper we propose a classification system with neural networks which reduces computational complexity through a pre-processing step (feature selection) performed by Bhattacharyya distance for image steganalysis. This approach is able to identify relevant features which are a subset of original features extracted from spatial as well as transform domain. It helps in overcoming the problem of "curse of dimensionalty" by removing redundant features by feature selection step before classifying the dataset. The experiments are performed on dataset obtained by four steganography algorithms outguess, steghide, PQ and nsF5 with two classifiers Support Vector Machine and Back Propagation neural networks. Classifier in combination with Bhattacharyya distance filter feature selection approach shows an improvement of 2-20% against total number of features.
The proceedings contain 50 papers. The topics discussed include: a rational multiparty information exchange model using extensive games;RSS-based secret key generation for indoor and outdoor WBANs using on-body sensor...
ISBN:
(纸本)9781509017775
The proceedings contain 50 papers. The topics discussed include: a rational multiparty information exchange model using extensive games;RSS-based secret key generation for indoor and outdoor WBANs using on-body sensor nodes;robust spectrum sensing algorithms under noise uncertainty;multicarrier modulation for HFe MANET in the Presence of communications;joint protection of a military formation using heterogeneous sensors in a mobile ad hoc network: concept and field tests;learning multi-channel power allocation against smart jammer in cognitive radio networks;and complex event processing for content-based text, image, and video retrieval.
暂无评论