Abstract—In this paper, the Cloud Image Processing and Analysis based Flatfoot Classification method that help doctors determine the flat feet is proposed. Via using image processing and analysis established on different virtual machines on cloud, the proposed method can remove noise and shape the images of the foot based on X-ray picture. The individual X-ray image after image processing is divided into four blocks according to the proposed division method which considering the percentage of each foot. By dividing the original image into four individual sub-partition of image, each divided image can be delivered to different analysis algorithms for key-point finding. Each image can be processed based on individual virtual machine on cloud. According to the proposed algorithms implemented on cloud for individual sub-partition of original image, the system can find four decision points of each block. Based on the integration of processing results from different algorithms, the system can automatically identify flat feet. Furthermore, the information and identification results can be provided to the doctor for further manual identification. In addition, the decision point can be also manually selected. In other words, according to the selection made by the doctor, the system can make the results more accurately and objectively. The simulation presents that the accuracy can be enhanced based on the dpi of the X-ray picture. Moreover, different methods used for decision points finding provide different performance. Keywords— Cloud, Edge Detection, Flatfoot, Medical Image Processing. Ming-Shen Jian is with the Department of Computer Science and Information Engineering, National Formosa University, Huwei, Yunlin, Taiwan, R.O.C. (e-mail: jianms@nfu.edu.tw). Jun-Hong Shen is with Department of Information Communication, Asia University, Wufeng, Taichung, Taiwan, R.O.C. (corresponding author) (phone: 886-4-23323456ext.20006; fax: 886-4-23305824; e-mail: shenjh@asia.edu.tw). Yu-Chih Chen is with the Department of Computer Science and Information Engineering, National Formosa University, Huwei, Yunlin, Taiwan, R.O.C. (e-mail: himaboy826@gmail.com). Chao-Chun Chang is with the Department of Computer Science and Information Engineering, National Formosa University, Huwei, Yunlin, Taiwan, R.O.C. (e-mail: wert943@gmail.com). Yi-Chi Fang is with the Department of Computer Science and Information Engineering, National Formosa University, Huwei, Yunlin, Taiwan, R.O.C. (e-mail: ken801227@gmail.com). Ci-Cheng Chen is with the Department of Computer Science and Information Engineering, National Formosa University, Huwei, Yunlin, Taiwan, R.O.C. (e-mail: q462246@gmail.com). Wei-Han Chen is with the Department of Computer Science and Information Engineering, National Formosa University, Huwei, Yunlin, Taiwan, R.O.C. (e-mail: k0937404150@gmail.com). I. INTRODUCTION A. Background and Motivation ith advances in technology, medical instrumentation and techniques are constantly improved. The medical image provided doctors a basis for illness detection. Since Rontgen discovered the X-ray, the demand on using X-ray to determine disease increases such as medical examination for military service. Currently, medical examination for military service such as flatfoot based on X-ray images becomes the main basis. However, such a huge number of medical images will result in the doctor's heavy burden. Therefore, via using an intelligent recognition system automatic analysis, doctors will be able to reduce the burden greatly. In addition, according to the consistent system in analyzing the images, the ratio of wrong identification for flatfoot can be reduced. Therefore, in this paper, we propose the flatfoot automatic classification method based on image recognition and analysis that includes image processing methods for the foot X-ray image, flatfoot determining algorithm, and measurement data providing. 1) Detection of flatfoot Flatfoot detection is often used in the military service medical examination and customized footwear. Because of the lack of a normal arch, walking and jogging will make foot more pressure, [3]. Those methods used to determine the flatfoot contains the following three ways: a. By the arch The arches of the foot are formed by the tarsal and metatarsal bones. The arch of flatfoot is too low. However, this method is detected by doctor's experience, with no real basis. Fig.1 shows the difference of normal and flat arch. Fig. 1 Difference of normal and flat arches Cloud Image Processing and Analysis Based Flatfoot Classification Method Ming-Shen Jian, Jun-Hong Shen, Yu-Chih Chen, Chao-Chun Chang, Yi-Chi Fang, Ci-Cheng Chen, Wei-Han Chen W INTERNATIONAL JOURNAL OF COMPUTERS Volume 8, 2014 ISSN: 1998-4308 90