We propose an effective 2d image based end-to-end deep learning model for malware detection by introducing a black & white embedding to reserve bit information and adapting the convolution architecture. Experimental results show that our proposed scheme can achieve superior performance in both of training and testing data sets compared to well-known image recognition deep learning models (VGG and ResNet).

This paper proposes a novel technology to detect the orientation of an image relying on its contour which is noised to varying degrees. For the image orientation detection, most methods regard to the landscape image and the image taken of a single object. In these cases, the contours of these images are supposed to be immune to the noise. This paper focuses on the the contour noised after image segmentation. A polar orientation descriptor Orientation Context is viewed as a feature to describe the coarse distribution of the contour points. This descriptor is verified to be independent of translation, isotropic scaling, and rotation transformation by theory and experiment. The relative orientation depends on the minimum distance Roulette Distance between the descriptor of a template image and that of a test image. The proposed method is capable of detecting the direction on the interval from 0 to 359 degrees which is wider than the former contour-based means (Distance Phase [1], from 0 to 179 degrees). What's more, the results of experiments show that not only the normal binary image (Noise-0, Accuracy-1: 84.8%) (defined later) achieves more accurate orientation but also the binary image with slight contour noise (Noise-1, Accuracy-1: 73.5%) could obtain more precise orientation compared to Distance Phase (Noise-0, Accuracy-1: 56.3%; Noise-1, Accuracy-1: 27.5%). Although the proposed method (O(op2)) takes more time to detect the orientation than Distance Phase (O(st)), it could be realized including the preprocessing in real time test with a frame rate of 30.

The Euler number of a binary image is an important topological property for pattern recognition, and can be calculated by counting certain bit-quads in the image. This paper proposes an efficient strategy for improving the bit-quad-based Euler number computing algorithm. By use of the information obtained when processing the previous bit quad, the number of times that pixels must be checked in processing a bit quad decreases from 4 to 2. Experiments demonstrate that an algorithm with our strategy significantly outperforms conventional Euler number computing algorithms.

Given a binary image I and a threshold t, the size-thresholded binary image I(t) defined by I and t is the binary image after removing all connected components consisting of at most t pixels. This paper presents space-efficient algorithms for computing a size-thresholded binary image for a binary image of n pixels, assuming that the image is stored in a read-only array with random-access. With regard to the problem, there are two cases depending on how large the threshold t is, namely, Relatively large threshold where t = Ω(), and Relatively small threshold where t = O(). In this paper, a new algorithmic framework for the problem is presented. From an algorithmic point of view, the problem can be solved in O() time and O() work space. We propose new algorithms for both the above cases which compute the size-threshold binary image for any binary image of n pixels in O(nlog n) time using only O() work space.

Many factors, such as noise level in the original image and the noise-removal methods that clean the image prior to performing a vectorization, may play an important role in affecting the line detection of raster-to-vector conversion methods. In this paper, we propose an empirical performance evaluation methodology that is coupled with a robust statistical analysis method to study many factors that may affect the quality of line detection. Three factors are studied: noise level, noise-removal method, and the raster-to-vector conversion method. Eleven mechanical engineering drawings, three salt-and-pepper noise levels, six noise-removal methods, and three commercial vectorization methods were used in the experiment. The Vector Recovery Index (VRI) of the detected vectors was the criterion used for the quality of line detection. A repeated measure ANOVA analyzed the VRI scores. The statistical analysis shows that all the studied factors affected the quality of line detection. It also shows that two-way interactions between the studied factors affected line detection.

Noise removal in engineering drawing is an important operation performed before other image analysis tasks. Many algorithms have been developed to remove salt-and-pepper noise from document images. Cleaning algorithms should remove noise while keeping the real part of the image unchanged. Some algorithms have disadvantages in cleaning operation that leads to removing of weak features such as short thin lines. Others leave the image with hairy noise attached to image objects. In this article a noise removal procedure called TrackAndMayDel (TAMD) is developed to enhance the noise removal of salt-and-pepper noise in binary images of engineering drawings. The procedure could be integrated with third party algorithms' logic to enhance their ability to remove noise by investigating the structure of pixels that are part of weak features. It can be integrated with other algorithms as a post-processing step to remove noise remaining in the image such as hairy noise attached with graphical elements. An algorithm is proposed by incorporating TAMD in a third party algorithm. Real scanned images from GREC'03 contest are used in the experiment. The images are corrupted by salt-and-pepper noise at 10%, 15%, and 20% levels. An objective performance measure that correlates with human vision as well as MSE and PSNR are used in this experiment. Performance evaluation of the introduced algorithm shows better-quality images compared to other algorithms.

Thinning and line extraction of binary images not only reduces data storage amount, automatically creates the adjacency and relativity between line and points but also provides applications for automatic inspection systems, pattern recognition systems and vectorization. Based on the features of construction drawings, new thinning and line extraction algorithms were proposed in this study. The experimental results showed that the proposed method has a higher reliability and produces better quality than the various existing methods.

In this study, a novel binary image authentication scheme is proposed, which can be used to detect any alteration of the host image. In the proposed scheme, the watermark is embedded into a host image using a Hamming-code-based embedding algorithm. A performance analysis shows that the proposed scheme achieves both smaller distortion and lower false negative rates than the previous schemes.

A new method for data hiding in binary images based on block pattern coding and dynamic programming with distortion-minimizing capabilities is proposed. Up to three message data bits can be embedded into each 22 block in an input image by changing the block's pixel pattern into another, which represents the value of the message data bits as a code according to a block pattern encoding table. And extraction of hidden message data is accomplished by block pattern decoding. To minimize the resulting image distortion, two optimization techniques are proposed. The first is to use multiple block pattern encoding tables, from which an optimal one is selected specifically for each input image, and the second is to use a dynamic programming algorithm to divide the message data into bit segments for optimal embedding in a sense of minimizing the number of binary bit flippings. Accordingly, not only more data bits can be embedded in an image block on the average, but the resulting image distortion is also reduced in an optimal way. Experimental results are also included to show the effectiveness of the proposed approach.

This paper presents novel algorithms for image restoration by state sharing methods with the stochastic model. For inferring the original image, in the first approach, a degraded image with gray scale transforms into binary images. Each binary image is independently inferred according to the statistical fluctuation of stochastic model. The inferred images are returned to a gray-scale image. Furthermore the restored image is constructed from the average of the plural inferred images. In the second approach, the binary state is extended to a multi-state, that is, the degraded image with Q state is transformed into n images with τ state and image restoration is performed. The restoration procedure is described as follows. The degraded image with Q state is prepared and is transformed into n images with τ state. The n images with τ state are independently inferred by the stochastic model and are returned to one image. Moreover the restored image is constructed from the average of the plural inferred images. Finally, the properties of the present approaches are described and the validity of them is confirmed through numerical experiments.

The skeleton and the skeleton function of an object are important representations for shape analysis and recognition. They contain enough information to recognize an object and to reconstruct its original shape. However, they are sensitive to distortion caused by rotation and noise. This paper presents another approach for binary object representation called a modified exoskeleton(mES) that combines the previously defined exoskeleton with the use of symmetric object whose dominant property is rotation invariant. The mES is the skeleton of a circular background around the object that preserves the skeleton properties including significant information about the object for use in object recognition. Then the matching algorithm for object recognition based on the mES is presented. We applied the matching algorithm to evaluate the mES against the skeleton obtained from using 4-neighbor distance transformation on a set of artificial objects, and the experimental results reveal that the mES is more robust to distortion caused by rotation and noise than the skeleton and that the matching algorithm is capable of recognizing objects effectively regardless of their size and orientation.

We prove that binary images of irreducible cyclic codes C over GF(2m) and binary concatenated codes of C and a binary [m+1,m,2] even-parity code are optimal (in the sense that they meet the Griesmer bound with equality) and proper, if a root of the check polynomial of C is primitive over GF(2m) or its extensions.

It becomes essential in practice to improve a processing rate and to divide an image into small segments adjusting a limited memory, because image filing systems handle large images up to A1 size. This paper proposes a new method of an automatic skew normalization, comprising a high-speed skew detection and a distortion-free dividing rotation. We have evaluated the proposed method from the viewpoints of the processing rate and the accuracy for typed documents. As results, the processing rate is 2. 9 times faster than that of a conventional method. A practical processing rate for A1 size documents can be achieved under the condition that the accuracy of a normalized angle is controlled within 0. 3 degrees. Especially, the rotation with dividing can have no error angle, even when the A1 size documents is divided into 200 segments, whereas the conventional method cause the error angle of 1. 68 degrees.

It is shown that five optimal and one quasioptimal binary codes with respect to the Griesmer bound can be obtained from cyclic codes over GF(2fm). An [m(2em - 1), em, 2em-1m] code, a [3(22e - 1), 2e, 322e-1] code, a [2(22e - 1), 2, (22e+2 - 4)/3] code, a [3(22e - 1), 2, 22e+1 - 2] code, and a [3(22e - 1), 2(e+1), 322e-1 - 2] code are optimal and a [2(22e - 1), 2(e + 1), 22e - 2] code is quasi-optimal.

As a new method to generate a homogeneous, random, binary image with a rational power spectrum, this paper proposes a discrete-valued auto-regressive equation, of which random coefficients and white noise excitation are all discrete-valued. The average and spectrum of the binary image are explicitly obtained in terms of the random coefficients. Some computer results are illustrated in figures.