Non-destructive Quality Evaluation of Chocolate Chip Cookies Parth Parikh UG student, EC Dept. G.H.Patel College of Engg. & Technology, V.V.Nagar, India parthparikh@yahoo.com Parth Mehta UG student, EC Dept. G.H.Patel College of Engg. & Technology, V.V.Nagar, India parth_mehta126@yahoo.com Dr. Chintan K. Modi Professor, EC Dept. G.H.Patel College of Engg. & Technology, V.V.Nagar, India chintankmodi@yahoo.com Abstract—Machine vision based non destructive quality evaluation of bakery products is important in terms of consumer satisfaction. The chocolate chip cookies need clear classification in terms of quality. To satisfy this need we need to consider more number of parameters to evaluate the quality. In this paper we propose to use four different parameters: number of chocolate chips, area efficiency of cookie, single chip area efficiency and uniform distribution of chocolate chips are defined. Based on them an overall quality parameter is defined. A novel and simple algorithm to evaluate the overall quality using machine vision techniques is proposed. Keywords: Quality control, Machine Vision, Chocolate chip cookies, Automatic thresholding method. I. INTRODUCTION Machine Perception is one of the fastest developing technologies in today’s world. It can be defined as the analysis of images to extract data for controlling a process or activity. Machine Vision processes are targeted at recognizing the actual objects in an image and assigning properties to those objects-- understanding what they mean. Image processing has become an important and convenient non contact method for quality evaluation and control in the food industry. Various applications of machine vision in the food industry include • Assessments of fruits and nuts.[1] • Vegetable inspection.[1] • Grain classification.[1] • Other processed foods like pizza, potato chips.[1] • Meat products.[1] • Quality evaluation of fennel seeds.[2] • Quality evaluation of olive oil conditioning.[3] Some of the researches done on the chocolate chip cookies include: • Colour bake inspection system using hybrid artificial neural networks.[4] • Fuzzy methods for automated inspection of food products.[5] • Fuzzy models to predict consumer ratings for biscuits based on digital image features.[6] • Invariant recognition of rectangular biscuits with Fuzzy moment descriptors, flawed pieces detection.[7] • Texture analysis for biscuit using Wavelet.[8] Considering the biscuit industry in specific, the various cookies and biscuits form an integral part of breakfast and snacks in most of the countries. Therefore, manufacturers in order to sustain in the tough competition, have to ensure superior quality in terms of physical appearance along with the hygiene and taste. India is one of the major producers and exporters of various forms of cookies. USA, Canada, Eastern and Central Africa and other major countries offer a huge market to the Indian biscuit industry. In this paper we propose four quality parameters to measure the quality of chocolate cookies and propose an algorithm to measure the quality of cookies. In section II of this paper we discuss the problem definition and its relevance in detail. Section III is a discussion of the tools used. The proposed algorithm for quality evaluation along with the proposed quality parameters is discussed in section IV. Section V contains the observations of applying the various tools and their analysis. Finally section VI concludes the paper followed by references. II. PROBLEM DEFINITION We define the problem as: to evaluate the quality of a chocolate chip cookie based on the number of chocolate chips, their size relative to the cookie itself, the chip area and their distribution relative to the cookie as a whole. Quality control is essential in the food industry and efficient quality assurance is becoming increasingly important. Consumers expect the best quality at competitive, affordable price along with a good shelf-life and taste satisfaction. In food industry most of the products are evaluated on the basis of human perception which can produce erroneous results. 2011 International Conference on Communication Systems and Network Technologies 978-0-7695-4437-3/11 $26.00 © 2011 IEEE DOI 10.1109/CSNT.2011.149 694