M. Ravishankar

Design of Novel Algorithm and Architecture for Gaussian Based Color Image Enhancement System for Real Time Applications

This paper presents the development of a new algorithm for Gaussian based color image enhancement system. The algorithm has been designed into architecture suitable for FPGA/ASIC implementation. The color image enhancement is achieved by first convolving an original image with a Gaussian kernel since Gaussian distribution is a point spread function which smoothen the image. Further, logarithm-domain processing and gain/offset corrections are employed in order to enhance and translate pixels into the display range of 0 to 255. The proposed algorithm not only provides better dynamic range compression and color rendition effect but also achieves color constancy in an image. The design exploits high degrees of pipelining and parallel processing to achieve real time performance. The design has been realized by RTL compliant Verilog coding and fits into a single FPGA with a gate count utilization of 321,804. The proposed method is implemented using Xilinx Virtex-II Pro XC2VP40-7FF1148 FPGA device and is capable of processing high resolution color motion pictures of sizes of up to 1600x1200 pixels at the real time video rate of 116 frames per second. This shows that the proposed design would work for not only still images but also for high resolution video sequences.

Ten-LoPP: Tensor Locality Preserving Projections Approach for Moving Object Detection and Tracking

In recent years, automatic moving object detection and tracking is a challenging task for many computer vision applications such as video surveillance, traffic monitoring and activity analysis. In this regard, many methods have been proposed based on different approaches. Despite of its importance, moving object detection and tracking in complex environments is still far from being completely solved for low resolution videos, foggy videos, and also Infrared video sequences. A novel scheme for Moving Object detection based on Tensor Locality Preserving Projections (Ten-LoPP) approach is proposed. Consequently, a Moving Object is tracked based on the centroid and area of a detected object. Numbers of experiments are conducted for indoor and outdoor video sequences of standard PETS, OTCBVS, Videoweb Activities datasets and also our own collected video sequences comprising partial night vision video sequences. Results obtained are satisfactory and competent. Comparative study is performed with existing well known traditional subspace learning methods.

A particle swarm optimization method for tuning the parameters of multiscale retinex based color image enhancement

In this paper, a Particle Swarm Optimization (PSO) method for tuning the parameters of multiscale retinex based color image enhancement is presented. The image enhancement using multiscale retinex scheme heavily depends on parameters such as Gaussian surround space constants, number of scales, gain and offset etc. Due to hard selection of these parameters, PSO has been used in order to investigate the optimal parameters for the best image enhancement. The PSO method of parameter tuning adopted for multiscale retinex with modified color restoration (MSRMCR) algorithm achieves very good quality of reconstructed images, far better than that possible with the other existing methods. The presented algorithm is compared with other promising enhancement schemes such as histogram equalization, NASAs multiscale retinex with color restoration (MSRCR), Improved MSRCR (IMSRCR), and Photoflair software. The quality of the enhanced image is validated iteratively using an efficient objective criterion which is based on entropy and edge information of an image. Finally, the quality of the reconstructed images obtained by the proposed method is evaluated using Wavelet Energy (WE) metric. The experimental results presented shows that color image enhanced by the proposed algorithm are clearer, vivid and efficient.

Recognition of machine printed broken characters based on gradient patterns and its spatial relationship

Recognition of degraded characters is a challenging problem in the field of document image analysis. Two main reasons for degradation of characters are due to noise scanning and intrinsic degradation caused by font variations. The degradation of characters is mostly in the form of characters being broken at several places which hinders their recognition of OCR systems. Many OCRs have been designed which correctly identify fine printed characters without any anomalies. However, very few research works has been reported on the recognition of the degraded character recognition due to its complexity. The efficiency of the OCRs system decreases if the input image is degraded and the characters are broken at several places, which frequently occur in old documents. In this paper, a novel approach based on slope pattern and its spatial relationship is used for recognizing broken characters. The proposed method is based on the computation of slope pattern of the individual characters in eight view-directions and generating image code for each character. The algorithm has been applied on the broken characters with successful results.

Automatic detection and tracking of moving objects in complex environments for video surveillance applications

Autonomous video surveillance and monitoring has a rich history. A new method for detecting multiple moving objects based on improved background subtraction model and for tracking is based on feature based approach has proposed. Then identified moving objects are also counted, by indexing individually. The proposed algorithm is automatic and efficient in intelligent surveillance applications like vehicles monitoring, event recognition, and crime prevention, etc. The proposed model has proved to be robust in various environments (including indoor and outdoor scenes) and different types of background scenes. Experiments on real scenes show that the algorithm is effective for object detection and tracking.

A new framework for retinex-based colour image enhancement using particle swarm optimisation

A new approach for tuning the parameters of multiscale retinex-based (MSR) colour image enhancement algorithm using a popular optimisation method, namely, particle swarm optimisation (PSO) is presented in this paper. The image enhancement using MSR scheme heavily depends on parameters such as Gaussian surround space constant, number of scales, gain and offset, etc. Selection of these parameters, empirically and its application to MSR scheme to produce inevitable results are the major blemishes. The method presented here results in huge savings of computation time as well as improvement in the visual quality of an image, since the PSO exploited maximises the MSR parameters. The objective of PSO is to validate the visual quality of the enhanced image iteratively using an effective objective criterion based on entropy and edge information of an image. The PSO method of parameter optimisation of MSR scheme achieves a very good quality of reconstructed images, far better than that possible with the other existing methods. Finally, the quality of the enhanced colour images obtained by the proposed method are evaluated using novel metric, namely, wavelet energy (WE). The experimental results presented show that colour images enhanced using the proposed scheme are clearer, more vivid and efficient.

Design and FPGA implementation of an 2D Gaussian surround function with reduced on-chip memory utilization

A new design and novel architecture suitable for FPGA/ASIC implementation of a 2D Gaussian surround function for image processing application is presented in this paper. The proposed scheme results in enormous savings of memory normally required for 2D Gaussian function implementation. In the present work, the Gaussian symmetric characteristics which quickly falls off towards plus/minus infinity has been used in order to save the memory. The 2D Gaussian function implementation is presented for use in applications such as image enhancement, smoothing, edge detection and filtering etc. The FPGA implementation of the proposed 2D Gaussian function is capable of processing (blurring, smoothing, and convolution) high resolution color pictures of size upto 1600×1200 pixels at the real time video rate of 30 frames/sec. The Gaussian design exploited here has been used in the core part of retinex based color image enhancement. Therefore, the design presented produces gaussian output with three different scales, namely, 16, 64 and 128. The design was coded in Verilog, a popular hardware design language used in industries, conforming to RTL coding guidelines and fits onto a single chip with a gate count utilization of 62,455 gates. Experimental results presented confirms that the proposed method offers a new approach for development of large sized Gaussian pyramid while reducing the on-chip memory utilization.

Natural Color Image Enhancement Based on Modified Multiscale Retinex Algorithm and Performance Evaluation Using Wavelet Energy

This paper presents a new color image enhancement technique based on modified modified MultiScale Retinex (MSR) algorithm and visual quality of the enhanced images are evaluated using a new metric, namely, Wavelet Energy (WE). The color image enhancement is achieved by downsampling the value component of HSV color space converted image into three scales (normal, medium and fine) following the contrast stretching operation. These downsampled value components are enhanced using the MSR algorithm. The value component is reconstructed by averaging each pixels of the lower scale image with that of the upper scale image subsequent to upsampling the lower scale image. This process replaces dark pixel by the average pixels of both the lower scale and upper scale, while retaining the bright pixels. The quality of the reconstructed images in the proposed method is found to be good and far better then the other researchers method. The performance of the proposed scheme is evaluated using new wavelet domain based assessment criterion, referred as WE. This scheme computes the energy of both original and enhanced image in wavelet domain. The number of edge details as well as WE is less in a poor quality image compared with naturally enhanced image. Experimental results presented confirms that the proposed wavelet energy based color image quality assessment technique efficiently characterizes both the local and global details of enhanced image.

LoG-DEM: Log Gabor filter and Dominant Eigen Map approaches for moving object detection and

In recent years, the numbers of Visual Surveillance systems have greatly increased, and these systems have developed into intellectual systems that automatically detect, track, and recognize objects in video. Automatic moving object detection and tracking is a very challenging task in video surveillance applications. In this regard, many methods have been proposed for Moving Object Detection and Tracking based on edge, color, texture information. Due to unpredictable characteristics of objects in foggy videos, the task of object detection remains a challenging problem. In this paper, we propose a novel scheme for moving object detection based on Log Gabor filter (LGF) and Dominant Eigen Map (DEM) approaches. Location of the moving object is obtained by performing connected component analysis. In turn, a Moving Object is Tracked based on the centroid manipulation. Number of experiments is performed using indoor and outdoor video sequences. The proposed method is tested on standard PETS datasets and many real time video sequences. Results obtained are satisfactory and are compared with existing well known traditional methods.

Multiple Moving Object Recognitions in Video Based on Log Gabor-PCA Approach

Object recognition in the video sequence or images is one of the subfield of computer vision. Moving object recognition from a video sequence is an appealing topic with applications in various areas such as airport safety, intrusion surveillance, video monitoring, intelligent highway, etc. Moving object recognition is the most challenging task in intelligent video surveillance system. In this regard, many techniques have been proposed based on different methods. Despite of its importance, moving object recognition in complex environments is still far from being completely solved for low resolution videos, foggy videos, and also dim video sequences. All in all, these make it necessary to develop exceedingly robust techniques. This paper introduces multiple moving object recognition in the video sequence based on LoG Gabor-PCA approach and Angle based distance Similarity measures techniques used to recognize the object as a human, vehicle etc. Number of experiments are conducted for indoor and outdoor video sequences of standard datasets and also our own collection of video sequences comprising of partial night vision video sequences. Experimental results show that our proposed approach achieves an excellent recognition rate. Results obtained are satisfactory and competent.