The image segmentation is a technique of image processing which divides image into segments. The many proposed image segmentation techniques, k-Means clustering has been one of the basic image segmentation techniques. The advantages of k-Means are easy calculation, the number of small iteration, and one of the most commonly used clustering algorithm. but, The main problem in this algorithm is sensitive to selection initial cluster center. In this research, we present two approaches method which are used to execute image. It is PSO and k-Means. k-Means integrated with Particle Swarm Optimization (PSO) to improve the accuracy. The purpose of this research to find the effect of PSO towards k-Means in order to get the best selection initial cluster center. This research has been implemented using matlab and taking image dataset from weizzmann institute. The Result of our experiment, we have different result RMSE of k-Means PSO. Euclidean has less RMSE value than Manhattan. The difference RMSE between Euclidean PSO and Manhattan PSO only four point. but if we compare by processing time we have significant difference.

Image Segmentation is one essential processing on moving object detection. The one of common segmentation methods is thresholding. In this paper, Thresholding method based on adaptive local technique using local mean and standard deviation is known as 'WAN' method. WAN has been inspired by the Sauvola's binarization method and exhibits its robustness and effectiveness when evaluated on low quality document images. The objective of the WAN to enhance the sauvola method and to get a better binarization result and enhance the accuracy. This research aims to produce output value of WAN algorithm. WAN would be compared to other existing adaptive local method like sauvola and niblack. This research is implemented by using matlab and four videos original from camera. The best result calculation error (MSE,PSNR) of WAN method are (0.0011, 53,6655). Overall, the result of WAN method in this paper is more effective and efficient than the other existing method based on MSE and PSNR.

Metode segmentasi kebanyakan digunakan dalam teknik pengolahan citra yang berkaitan dengan deteksi objek bergerak. Segmentasi pada objek bergerak sangat penting untuk menentukan proses selanjutnya berupa pengenalan atau klasifikasi. Metode yang paling umum digunakan dalam teknik-teknik segmentasi adalah metode pengambangan. Metode pengambangan dibagi menjadi dua yaitu global dan lokal. Pada penelitian kali ini akan mencoba menggunakan salah satu metode pengambangan lokal adaptif yaitu sauvola. Sauvola akan digunakan sebagai nilai ambang dari background subtraction. Garis besar dari metode yang diusulkan dalam penelitian ini adalah ekstraksi frame, inisialisasi background, preprocessing, background subtraction, sauvola, pemberian masking. Hasil terbaik rata-rata MSE dan PSNR adalah 0.0011 dan 53,6653. Pengambangan dengan sauvola mendapat hasil cukup baik dan layak sebagai nilai ambang dari background subtraction.

No abstract