ISSN: 2278 – 1323 International Journal of Advanced Research in Computer Engineering & Technology (IJARCET) Volume 2, Issue 3, March 2013 891 All Rights Reserved © 2013 IJARCET Abstract— The inspection of product quality in majority of cases is based on human factor because of complexities of problems of inspection and quality and demands for the changeability during decision about the quality of product. As the product comes from automated production chain to final manufacturing line its surface and edges are inspected by the stuff employed to detect the defects. In order to avoid human errors in the system, complete automation of production is required. Digital image segmentation can be a versatile, reliable and a low-cost tool for the quality identification of materials, with the potential to replace other all other costly techniques. In this paper, select different types of materials like tiles and rods, the images are acquired and calibrated. The image without defect is kept as a reference image. Then the sample which is to be tested is checked by comparing with the reference image by using techniques like Thresholding, Histograms and Spatiogram Similarity and Cell Segmentation in Matlab environment. The variation in the images shows the defect in the material. By using this system can identify the quality of the industrial materials. The same procedure can also be adopted with digital camera for the quality identification of various other industrial materials. The design based on using FPGA for the hardware implementation of the architecture using VHDL. FPGA Spartan 3E starter Kit has been used for the hardware implementation. The proposed method is an improvement over traditional software package based approaches in that of image comparison. Index Terms— DIP, FPGA, Rod surface, Threshold value. I. INTRODUCTION The various industrial sectors have taken significant advantage of the strong evolution in the world of automation in recent years. All production phases have been addressed through various technical innovations, with the exception of the final stage of the manufacturing process. This is still performed manually and is concerned with visual surface inspection. A new technique to solve these problems is to use Digital Cameras in place of analog sensors. The digital images are taken and continuously transmitted to the operator station. Digital image processing pays way for generating control signals by comparing the just received image with the standard image already stored inside the computer. Photographs are taken through digital cameras of different levels of adulteration they are stored inside the computer as an G.Rajakumar is with the Francis Xavier Engineering College, Tamil Nadu, India. Dr.D.Manimegalai is with the National Engineering College, Tamil Nadu, India. experimental setup. In the normal checkup the liquid photograph is taken and is compared with the already stored image inside the PC and a signal is generated when it matches the image. This indicates the defect even when it is very small [1]-[3]. In the proposed systems segmentation is the process of partitioning a digital image into multiple segments (sets of pixels, also known as super pixels). The goal of segmentation is to simplify and change the representation of an image into something that is more meaningful and easier to analyze. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. More precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain visual characteristics. The result of image segmentation is a set of segments that collectively cover the entire image, or a set of contours extracted from the image. Each of the pixels in a region is similar with respect to some characteristic or computed property, such as color, intensity, or texture. Adjacent regions are significantly different with respect to the same characteristics [4]-[5]. The proposed work is photographs (field images) taken through web camera (digital signal) connected to computer. Super imposing of actual images in the mimic diagram. The field images (just received) are compared with the Standard images already stored in the computer. Identification action is initiated when both images matches. Slowly analog transducer can come to a halt. The emerging DIP technologies will revolutise the present control system. This paper discusses the VLSI Implementation of DIP Based Rod Quality Identification. In Section II, VLSI Based Proposed Systems is presented. In Section III, Results and Discussions are discussed. In Section IV, conclusions are drawn. II. VLSI BASED PROPOSED SYSTEMS The general hardware setup of the proposed system is Camera is placed 20 cm altitude from the bottom of the stand. The intensity of light source is 10 candelas and maintained the room temperature. The bottom surface color is white. The samples are placed at glass on the white surface. First, Cross sectional view of Steel Rod Surface Reference image is taken by camera and converted in to bit file format then stored in Field Programmable Gate Array (FPGA). Next, various level of human eyes are can‟t identify the crack in the Cross sectional view of Steel Rod Surface Sample image is taken by camera and converted in to bit file format provide to FPGA. Finally, Cross sectional view of Steel Rod Surface Reference image is compared to Cross sectional view of Steel Rod Design and VLSI Implementation of DIP Based Rod Quality Inspection G.Rajakumar, Dr.D.Manimegalai