International Journal of Recent Technology and Engineering (IJRTE) ISSN: 2277-3878, Volume-8 Issue-2S8, August 2019 1391 Published By: Blue Eyes Intelligence Engineering & Sciences Publication Retrieval Number: B10730882S819/2019©BEIESP DOI:10.35940/ijrte.B1073.0882S819 Abstract: In this paper, an implementation of image processing methods to extract and recognize a standard tri-colored archery target to a field-programmable gate array is demonstrated. Detection and recognition of the archery target was never been done on an FPGA platform. The platform used to realize the design was the ZedBoard™ Development Kit equipped with Xilinx Zynq®-7000 All Programmable system on chip. The algorithms used to extract the central region is based on color classification in HSV color space. Once each image pixels are classified, the color sequence recognition algorithm attempts to look for the target and extract the central region of the archery target if present. Image filtering techniques and analysis such as morphological filtering and contour feature analysis are used to properly identify the shape and location of the extracted pixels. Discussed next is the implementation of the algorithm both in the software and hardware aspects and a comparison between their response time and accuracy is demonstrated. There was about two-fold decrease in processing time when FPGA implementation was deployed. The accuracy of the system was also tested and able to reach an accuracy of 96.67% for near target distance. For far target distance, the accuracy degraded to 88.33% but the system has managed to maintain its specificity value despite the noise becoming dominant for smaller region occupied by the target. Keywords: Archery target, Color classification, Color sequence recognition, Field-programmable gate array, Image processing. 1. INTRODUCTION A growing interest in the field of robotics is to mimic the human abilities and ultimately outperform them in different skills such as shooting an arrow accurately to a target. In such a robot, an ability to detect and recognize the central golden region of the archery target is of utmost importance to meet these human feats. A study in [1] shows a humanoid robot capable of learning to shoot more accurately as it is exposed to archery shooting tasks. Demonstration of this capability of robots was also demonstrated in [2]. The objective if these studies can only be achieved if appropriate image processing of the target and the arrow were available and reliable. As such, appropriate image processing methods are needed to realize this objective. There are a handful of studies on image Revised Version Manuscript Received on August 19, 2019. Dino Dominic Ligutan, ECE Department, De La Salle University, Manila, Philippines. Alexander C. Abad, ECE Department, De La Salle University, Manila, Philippines. Melvin Cabatuan, ECE Department, De La Salle University, Manila, Philippines. Cesar Llorente, ECE Department, De La Salle University, Manila, Philippines. Elmer P. Dadios, MEM, Department, De La Salle University, Manila, Philippines. processing methods applied to the archery target. Most of these studies pertains to automatic scoring system; that is, to provide an automated solution to determine the score of a shot arrow on a target. The study in [3] describes an algorithm to rectify the archery target for different viewing angles as well as recognize the shot arrows embedded within and by approximating their positions relative to the target center as a basis for scoring. Detecting the point at which the arrow struck the target is a non-trivial task for image processing and is very much affected by many factors such as lighting condition and viewing angle. Another automatic scoring system by [4] provides a very different approach in scoring arrows that is dependent on background subtraction and morphological operations to detect the target and then the arrow through the process of arrow head nomination. However, the study used a much higher frame resolution and achieved a higher accuracy rate than the former. This study was taken further by proposing a new algorithm for real-time arrow detection and scoring using the concept of score region images. [5] All of these studies however are limited to stationary archery targets only. Furthermore, the systems developed are implemented on a conventional computing device that operates in full dependence of software algorithms. On the other hand, there are numerous image processing algorithms were already implemented on FPGA to take advantage of parallel processing that it offers. The study on [6] has implemented several image processing modules on an FPGA that can be used for a variety of settings. The system was reconfigurable and specific image processing can be chosen easily depending on the application at hand. Similar purpose was also achieved in [7] is optimized through implementation of different architectures at the block level. Besides the need for faster color recognition, FPGA was utilized not only to recognize colors but to track motion as well [8] to serve as an input for robot formation control to guide their motion in real-time. Another study [9] also demonstrated the possibility of an efficient color conversion from YCbCr to RGB so that it becomes easier for standard algorithms to identify and calibrate color detection for different display devices. Color recognition and classification has diverse applications that several studies were conducted [10]–[13] due to the necessity of a far more faster processing of continuous stream of images on real-time applications. FPGA Implementation of Archery Target Detection using Color Sequence Recognition Algorithm Dino Dominic Ligutan, Alexander C. Abad, Melvin Cabatuan, Cesar Llorente, Elmer P. Dadios