Prompt Indian Coin Recognition with Rotation Invariance using Image Subtraction Technique Vaibhav Gupta, Rachit Puri, Monir Verma Electronics and Communication Engineering Department Thapar University, Patiala -147001, India gupta.vaibhav.17@gmail.com, rachitpuri19@gmail.com, monirverma@gmail.com Abstract – This paper detects Indian coins of different denomination. The spiraling business transaction at vending machines and automated systems working on token have spurred better coin recognition techniques saddled with increased robustness. These techniques facilitate transaction making it easier in all forms of trade. Keeping all the essential factors in mind a system has been created which recognizes coin based on image subtraction technique. The process performs 3 checks (radius, coarse and fine) on the input image. The stated subsequent checks enable the technique to endorse Rotation Invariance, thus obviating the need of placing the coin at a certain angle. Also, the technique does away with the requirement of placing the front face of the coin up. Subtraction between the input object image and database image is performed. Further, plotting the resultant values gives minima which if less than a standard threshold establishes the recognition of the coin. Results of MATLAB based simulations have been reported. Keywords – Image Segmentation, Image subtraction, Object Detection. I. INTRODUCTION Humans easily recognize familiar patterns or objects regardless of their size or orientation differences. This is due to our intelligent system of perception which has been trained to recognize the objects over time. However, we are able to simulate our perception of objects and pattern recognition in intelligent machines using trained neural networks [1]. The paper proposes a coin recognition method using image subtraction technique which has an advantage over the conventional identification methods used commonly in slot machines. Most of the coin testers in slot machines, work by testing physical properties of coins such as size, weight and materials. However, if physical similarities exist between coins of different currencies, then the traditional coin testers would fail to distinguish the different coins. The image subtraction technique takes two images as input and gives a third image as output, whose pixel values are simply the pixel values of the first image minus the corresponding pixel values of the second image. Modus operandi consists of the stated technique. It also incorporates the radius check which would assist in choosing the befitting coin from the database. Database amasses the standard coin used for recognizing the input image. Images formulating the database are taken under standard conditions including the distance, background and lighting. Once the precise image is selected, its feature are extracted (explained in II) and subtracted from the input coin image (referred to as object image). Image rotation invariance is introduced by rotating the image at fixed angular interval thus providing us with the exact angle of difference between the coins on analyzing the plot of the subtracted values [2, 3]. Extracting the minima of the plot and on comparing it with a standard threshold value, the object coin can be determined as coin of same denomination or not. Thus, coin stands recognized. Fig. 1 Front side of various Indian coins Fig. 2 Back side of various Indian coins Many pattern recognition systems insensitive to transformation of an input pattern have now been presented. P. Thumwarin [4] presented the rotation invariance feature by the absolute value of