Digital Image Processing

Farheen K. Siddiqui ¹, Vineet Richhariya ²

Affiliations
1 Lakshmi Narayan College of Technology, Bhopal, MP, IN
2 Computer Science Department in Lakshmi Narayan College of Technology, Bhopal, MP, IN

Abstract

Image segmentation is vital step in the process of image processing, which is at the middle layer of image engineering. An outline of the development of image segmentation in the recent years is analyzed. This paper gives a deeper analysis of the topic along with the various techniques being worked out in the recent years. Several thousands of segmentation algorithms have been designed and applied for various applications, and this number has increased steadily making it quite hard to work out a comprehensive survey and a suitable classification scheme for hierarchical categorizing the whole techniques. Each method has its own advantages and disadvantages to be use in different problem areas. Accuracy, complexity, efficiency and interactivity of a segmentation method should all be the considered factors. The domain of image segmentation is still immature. Many unsettled problems need to be defined and solved in this area. It is firmly believed that this domain will greatly advance in the future. This evaluation may prove to be an essential step for the development and improvement of new techniques in this area.

Keywords

Segmentation, Image Processing, Clustering, Region Based, Threshold Based, Watershed.

Full Text

     

Farheen K. Siddiqui ¹, Vineet Richhariya ²

Affiliations
1 Lakshmi Narayan College of Technology, Bhopal, MP, IN
2 Computer Science Department in Lakshmi Narayan College of Technology, Bhopal, MP, IN

Abstract

Image segmentation is a significant task for image analysis which is at the middle layer of image engineering. The purpose of segmentation is to decompose the image into parts that are meaningful with respect to a particular application, very much like the idea of separating figure from ground. With the advance in color image technology and its application in various areas, several techniques have been formulated. The proposed system is to boost the morphological watershed method for degraded images. The watersheds transformation is an effective method for extracting out continuous boundaries of each region and gives solid results. However, some of the issues concerned with it are, over segmentation and ambiguous boundary on homogeneous regions. Proposed algorithm is based on merging enhanced morphological watershed result with enhanced edge detection result obtain on pre processing of degraded images. Here preprocessing means image restoration. Hence it enhances the watershed result. As a post processing step, to each of the segmented regions obtained, color histogram algorithm is applied i.e computing the JND histogram followed by the agglomeration of the histograms which can be thought of as the powerful alternatives to the other image thresholding techniques. This stimulates the process of merging of small left over segments with larger similar segments, enhancing the overall performance of the watershed algorithm. The Segmentation algorithm is more computationally efficient, its edge- preserving, noise removing, shape maintaining features are remarkable than many top-ranking image segmentation algorithms.

Keywords

Segmentation, Watershed Algorithm, Color Histogram, Morpho-Logical Operations, Gradient Image.

Full Text

     

Tanvi Chauhan ¹, Vineet Richhariya ²

Affiliations
1 Department of Engineering, Lakshmi Narain College of Technology, Bhopal-(M.P), IN
2 Department of Engineering, Lakshmi Narain College of Technology, Bhopal (M.P), IN

Abstract

Face recognition in video has gained wide attention as a covert method for surveillance to enhance security in variety of application domains (e.g., airports, traffic, Terrorist attack).A video contains temporal information as well as multiple instances of a face, so it is expected to lead to better face recognition performance compared to still face images. However, faces appearing in a video have substantial variations in pose and lighting. We propose a face recognition system that identifies faces in video. The system utilizes the rich information in video. The description of the proposed method and preliminary results are provided.

Keywords

Face Detection, Image Enhancement, Skin Color Detection, Feature Extraction, Pattern Recognization, Luminance, Color Transform.

Full Text