International Association of Scientific Innovation and Research (IASIR) (An Association Unifying the Sciences, Engineering, and Applied Research) International Journal of Emerging Technologies in Computational and Applied Sciences (IJETCAS) www.iasir.net IJETCAS 12-348; © 2013, IJETCAS All Rights Reserved Page 155 ISSN (Print): 2279-0047 ISSN (Online): 2279-0055 Preprocessing of chili pepper images Segmentation of Chili pepper seeds Feature extraction and classification of chili seeds Recognition with neural network Output Noise Removal Methods of Chili Pepper Images for Detecting Toxin Using Neural Networks M.Rajalakshmi 1 Research Scholar Dr.P.Subashini 2 Professor Department of Computer Science, Avinashilingam Deemed University, Coimbatore -43. Tamilnadu, India. Abstract: Mycotoxins are toxic substances produced mostly as secondary metabolites by fungi that grow on seeds and feed in the field, or in storage. The food-borne Mycotoxins likely to be of greatest significance for human health are Aflatoxin and Fumonisins. Chili pepper is also affected by Aflatoxin contamination during harvesting, production and storage periods. X-ray is a very popular non-destructive testing method. In this proposed work, X-ray images of chilli pepper samples were collected and processed using image processing methods. This research paper gives a review of existing approaches of pre-processing methods compared with the proposed 4-connected median filter. Based on the performance measure analysis the best pre-processing method is selected, to remove the noise presence in chili pepper X-ray images. Keywords: Aflatoxin, Chili pepper, image enhancement, performance measures of X-ray images, threshold I. Introduction Accessing high quality and safe food is one of the most important things to the public anxiety in recent decades. Food safety implies that the food includes safe levels of the substances, which does not include toxins and contaminants cause injurious to human health. Food quality includes characteristics such as nutritional value and texture for the food to be preferred by the consumers. Many countries impose strict control on the standards of food contents which directly affect the health and quality. It is essential to all the countries to assure the safety and quality of the imported food to protect their domestic consumers. In addition to the domestic consumers more attention should be given to the safety and quality of export food in the global market [7]. A. Non-destructive methods Non-destructive methods are a part of quality control function and complementary to other established methods to maintain better quality of the products. Non-destructive testing is the testing of materials in the surface or internal faults or to find purifying and alloying metals condition, without interfering in any way with the reliability of the material or its suitability for service. This method is suitable for testing the sample units individually or the entire production units for the quality control centre. Due to development of high technology and evolution of equipments, huge quality control applications in the lead-time of production sectors. To facilitate production the application of this method requires certain degree of skills to obtain more information about the manufactured product. To improve the product requires consequent feedback from the quality control centre [7]. After the detailed study of the previous researches, the proposed system is as follows in fig1. Fig. 1. Proposed system Chili Pepper Image acquisition