An automatic photo retrieval system based on a face sketch has very useful application as to narrow down potential suspects in criminal investigations. This is true when there is no other evident except the face sketch that is rendered based on the recollection of a victim or eyewitness. Among the noticeable difficulties in matching the sketch and photo due to its modality difference are the generated sketch has some tendency of shape exaggeration, the sketch has very less accurate details and the real-world photo may expose to lighting variation unlike the sketch. In this paper, we attempt to address these complications by matching the sketch and photos using dynamic local feature of Difference of Gaussian Oriented Gradient Histogram (DoGOGH) on some selected patches. To avoid discriminative power degradation due to a large number of gallery images, two stage matching blocks are introduced in a cascaded fashion. The front block matches the feature such that it short lists k most similar photos for the second block. In this front block, Histogram of Oriented Gradient (HOG) and Gabor Wavelet (GW) features are fused by maximizing the correlation between the two using Canonical Correlation Analysis (CCA). Based on the short listed photos, the following block re-matched the sketch and photos using dynamically extracted local feature on its Patch of Interest (PoI). Eventually, the matching scores from the blocks are fused before getting rank-1 accuracy. The experimental results on two baseline datasets indicate that the proposed method outperforms the stateof-the-art methods. The extended evaluation on semi-forensic and forensic sketch datasets demonstrate its usage feasibility.

No abstract

No abstract

No abstract

The main objective of this study is to compare the execution times produced by fending off techniques of Seni Silat Cekak Malaysia (SSCM), Kaedah A for different movement trajectories. Three kind of movement trajectories for Kaedah A were carried out which were Trajectory A (normal path), Trajectory B (curve path) and Trajectory C (starting by pulling the hand to the back and continue as Trajectory A). The experiments were conducted using motion capture system where the movement position of the left hand during the execution of Kaedah A were recorded by Kinect sensor, prior to storing and processing via Virtual Sensei (VS) Lite software. A total of four (4) experienced practitioners from SSCM with their consent were selected to perform Kaedah A techniques. The data acquired were further analyzed to determine their kinematic characteristics. Results showed that the execution of Kaedah A using Trajectory A produced the shortest time and highest velocity with average of 0.071±0.007s and 6.438±0.863ms-1 respectively, compared to Trajectory B (0.087±0.011s, 5.230±0.578 ms-1) and Trajectory C (0.149±0.015s, 2.903±0.273ms-1). Therefore, Trajectory A is considered to be more efficient than Trajectory B and Trajectory C in terms of execution times and maximum velocity produced by Kaedah A.