Panca Mudjirahardjo

Comparison of feature extraction methods for head recognition

Feature extraction plays an important role in head recognition. It transforms an original image into a specific vector to be fed into a classifier. An original image cannot be further processed directly. Raw information in an original image does not represent a specific pattern and a machine cannot understand that information. In this paper, we propose a novel feature extraction method for human head recognition and perform a comparison of the existing image features extraction methods using a static image. The existing features are HOG and LBP, and the proposed feature is a histogram of transition. A histogram of transition is based on calculation of a transition feature. A transition feature is to compute the location and the number of transitions from background to foreground along horizontal and vertical lines. So, this transition feature relies on foreground extraction. In design, the proposed feature has the number of arrays less than the existing features, and the computation of feature transition is simpler than the existing features. These conditions give the computation of the proposed feature faster than the computation of existing features. The recognition rates using the proposed feature are that the head recognition rate is 91% and the non-head recognition rate is 99.7%. The execution time is 0.077 ms. These performances show that the proposed feature can be used for real time application.

Temporal analysis for fast motion detection in a crowd

Abstract We present a fast motion detection technique in a crowd as an abnormal motion based on optical flow and a motion history image (MHI). Since a camera view is usually not in perpendicular with motion direction, the velocity of motion is not uniform spatially. Instead of object detection directly from an image, we separate an image into several blocks. In this paper, we propose a novel method to analyze a motion using MHI representation, called a shift space and a shift histogram. Together with a velocity histogram, the method can detect fast motion in a crowd, realizing local abnormal event detection. The performance of the proposed method is experimentally illustrated and evaluated.

Real time object localization based on histogram of s-RGB

Object localization is the first task in pattern detection and recognition. This task is very important due to it reduces the searching time to the interest object. In this paper we introduce our novel method of object localization based on color feature. Our novel method is a histogram of s-RGB. This histogram is used in the training phase to determine the color dominant in the initial Region of Interest (ROI). Then this information is used to label the interest object. To reduce noise and localize the interest object, we apply the row and column density function of pixels. The comparison result with some processes, our system gives a best result and takes a short computation time of 26.56 ms, in the video rate of 15 frames per second (fps).