Ayan Chaki

Information Measure Ratio Based Real Time Approach for Hand Region Segmentation with a Focus on Gesture Recognition

This paper presents an efficient and real time novel approach for hand region segmentation with an aim to achieve hand gesture recognition under varying illumination. The overall methodology is a two step process: (a) to achieve the segmentation of the hand from the complex background and (b) to recognize the hand gesture efficiently and accurately. Hand segmentation is achieved using block based picture information ratio and recognition is done using Principal Component Analysis (PCA). In the experimental results four basic hand gestures have been considered which were recognized consistently in complex but near constant background and varying illumination. The prototype has been developed in X86, tested with live videos captured by low cost web cams . It performs with 98% accuracy in real time.

An application for retrieval of frames from a laparoscopic surgical video based on image of query instrument

This paper describes a practical and reliable solution/approach to achieve automated retrieval of surgical instruments used in laparoscopic surgery. The central goal is to locate particular video frames containing intended information which can be used for analysis and diagnosis. In this paper, a practical system is proposed where the users need not manually search the candidate frames in the entire video. Instead, users can give any query object (in image format) and the frames containing the object will be retrieved. Given an object image, the method extracts features like color and shape of objects in each frame of the laparoscopic video and compare with the input image feature to retrieve the frames containing the desired instrument. The system can recognize the instrument in 91% cases but does not give any false alarm. Experimental results are presented to show the feasibility of the proposed application.

A Fast Method for Detection of Video Shot Boundaries Using Compressed Domain Features of H.264 for PVR Enabled Set Top Boxes: A Novel Approach

In this paper authors have proposed an algorithm to automatically identify video shot boundaries using compressed domain features of H.264. In this method the compressed domain features of H.264 video obtained during encoding the video data is used to identify the shot boundaries. The features used in our approach are (i) Number of I Macroblocks (MBs) in a P frame, (ii) No of Sub-blocks containing strong de-blocking filter edges and (iii) DC component of integer transformed luma coefficients. We compare these features in every two consecutive frames of video to decide whether there is a shot boundary or not. Experimental results show that the proposed approach can work in real time in any commercially available DSP platform and can detect the shot boundaries successfully. The system on different type of videos gives a recall rate of 1.0 and a precision rate of .877.

Recognition of Ingredients and Recipes of Cookery Shows for Value Added Service (VAS) of an Interactive Set Top Box (iSTB)

In this paper authors have proposed a VAS for Personal Video Recorder (PVR) enabled iSTB. The proposed solution can recognize the regions in the frames where the recipe and ingredients are shown and can save them in image/text format for further use. We have used a hybrid approach where the text regions are localized using the compress domain features of the streaming video in real time and then some pixel domain processing is performed on that reduced region of interest to recognize the text. The novelty of the proposed approach lies in using the compressed domain features of H.264 video in text localization and applying some pixel domain post processing on the ROI to perform the entire recognition process in real time. The system is tested over a video upto CIF resolution and can recognize the text successfully with an accuracy of nearly 80%.

An intelligent fuzzy multifactor based decision support system for crack detection of underground sewer pipelines

This paper describes a practical and reliable solution/approach to achieve a semi-automated sewer pipeline inspection. The central goal of this work is to detect faults in the sewer lines which are a potential threat for underground drainage system. The major challenge for sewer line inspection is the classification and interpretation of the image data that are captured mainly by CCTV cameras mounted on robots. In this paper we had focused on providing the human operators a tool based on image processing technology that will help them to take decision on the pipe quality. The approach in this paper involves segmentation of the sewerage images based on prior knowledge of the defects. In this paper, a multi-factorial based approach has been proposed where the decision taking process involves a fuzzy mechanism based on weighted values of different parameters.

A Comprehensive Market Analysis on Camera and Illumination Sensors for Image Processing and Machine Vision Applications

In the present industrial application space, conventional inspection techniques using manual intervention are getting replaced by automated inspection using image sensors. Image sensors have empowered machines with vision and that has led to increased levels of process automation which used to be manually exhaustive. This paper mainly focuses on the comparative study of Machine Vision hardware aspect specifically on cameras and lighting- the technologies in use and their application across different industry verticals.

An Automatic decission support system for medical instrument suppliers using fuzzy multifactor based approach

Most products are inspected for flaws several times during the manufacturing process. For this purpose, object detection is a very fundamental task in most of the image analysis applications. Most of the existing methods for low-level object detection perform color similarity and histogram similarity based approach in the 2-D image space. In this paper, a multi-factorial based approach has been proposed where the decision taking process involves a fuzzy mechanism based on weighted values of different parameters.