• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권7호
• /
• pp.3654-3670
• /
• 2019

This paper proposes an Image Texture Median Filter (ITMF) to analyze and detect Android malware on Drebin datasets. We design a model of "ITMF" combined with Image Processing of Median Filter (MF) to reflect the similarity of the malware binary file block. At the same time, using the MAEVS (Malware Activity Embedding in Vector Space) to reflect the potential dynamic activity of malware. In order to ensure the improvement of the classification accuracy, the above-mentioned features(ITMF feature and MAEVS feature)are studied to train Restricted Boltzmann Machine (RBM) and Back Propagation (BP). The experimental results show that the model has an average accuracy rate of 95.43% with few false alarms. to Android malicious code, which is significantly higher than 95.2% of without ITMF, 93.8% of shallow machine learning model SVM, 94.8% of KNN, 94.6% of ANN.

• 한국통신학회논문지
• /
• 제34권4C호
• /
• pp.371-379
• /
• 2009

본 논문에서는 텍스쳐 감지를 이용한 화소값 기울기 필터 및 중간값 필터 기반의 비디오 시퀀스 디인터레이싱 알고리듬을 제안한다. 먼저 보간 할 픽셀의 주변 픽셀들을 이용하여 현재 보간 할 영역이 텍스쳐가 존재하는 영역인지 아니면 평탄한 영역인지를 판단한다. 제안하는 알고리듬에서는 보간 할 영역이 평탄한 영역으로 판단되면 중간값 필터를 이용하여 보간을 하고, 텍스쳐 영역으로 판단되면 화소값 기울기 필터를 이용하여 보간을 하게 된다. 그러므로 현재의 보간 할 영역은 두 개의 카테고리로 분류 할 수 있다. 제안하는 알고리듬은 상황에 맞게 적응적으로 보간을 수행하므로 좀 더 선명하고 정확한 영상을 얻을 수 있다. 그리고 여러 가지 CIF 동영상에 대한 실험 결과는 제안하는 알고리듬이 기존의 알고리듬 보다 객관적, 주관적으로 우수함을 보여준다.

• Journal of information and communication convergence engineering
• /
• 제8권6호
• /
• pp.645-650
• /
• 2010

In this paper, we present the effect of binocular cues which plays crucial role for the visualization of a stereoscopic or 3D image. This study is useful in extracting depth and disparity information by image processing technique. A linear relation between the object distance and the image distance is presented to discuss the cause of cybersickness. In the experimental results, three dimensional view of the depth map between the 2D images is shown. A median filter is used to reduce the noises available in the disparity map image. After the median filter, two filter algorithms such as 'Gabor' filter and 'Canny' filter are tested for disparity visualization between two images. The 'Gabor' filter is to estimate the disparity by texture extraction and discrimination methods of the two images, and the 'Canny' filter is used to visualize the disparity by edge detection of the two color images obtained from stereoscopic cameras. The 'Canny' filter is better choice for estimating the disparity rather than the 'Gabor' filter because the 'Canny' filter is much more efficient than 'Gabor' filter in terms of detecting the edges. 'Canny' filter changes the color images directly into color edges without converting them into the grayscale. As a result, more clear edges of the stereo images as compared to the edge detection by 'Gabor' filter can be obtained. Since the main goal of the research is to estimate the horizontal disparity of all possible regions or edges of the images, thus the 'Canny' filter is proposed for decipherable visualization of the disparity.