YOLSO: You Only Look Small Object

Small object detection is challenging and far from satisfactory. Most general object detectors suffer from two critical issues with small objects: (1) Feature extractor based on classification network cannot express the characteristics of small objects reasonably due to insufficient appearance information of targets and a large amount of background interference around them. (2) The detector requires a much higher location accuracy for small objects than for general objects. This paper proposes an effective and efficient small object detector YOLSO to address the above problems. For feature representation, we analyze the drawbacks in previous backbones and present a Half-Space Shortcut(HSSC) module to build a background-aware backbone. Furthermore, a coarse-to-fine Feature Pyramid Enhancement(FPE) module is introduced for layer-wise aggregation at a granular level to enhance the semantic discriminability. For loss function, we propose an exponential L1 loss to promote the convergence of regression, and a focal IOU loss to focus on prime samples with high classification confidence and high IOU. Both of them significantly improves the location accuracy of small objects. The proposed YOLSO sets state-of-the-art results on two typical small object datasets, MOCOD and VeDAI, at a speed of over 200 FPS. In the meantime, it also outperforms the baseline YOLOv3 by a wide margin on the common COCO dataset.     

Enhanced wide-activated residual network for efficient and accurate image deblocking

To save bandwidth and storage space as well as speed up data transmission, people usually perform lossy compression on images. Although the JPEG standard is a simple and effective compression method, it usually introduces various visually unpleasing artifacts, especially the notorious blocking artifacts. In recent years, deep convolutional neural networks (CNNs) have seen remarkable development in compression artifacts reduction. Despite the excellent performance, most deep CNNs suffer from heavy computation due to very deep and wide architectures. In this paper, we propose an enhanced wide-activated residual network (EWARN) for efficient and accurate image deblocking. Specifically, we propose an enhanced wide-activated residual block (EWARB) as basic construction module. Our EWARB gives rise to larger activation width, better use of interdependencies among channels, and more informative and discriminative non-linearity activation features without more parameters than residual block (RB) and wide-activated residual block (WARB). Furthermore, we introduce an overlapping patches extraction and combination (OPEC) strategy into our network in a full convolution way, leading to large receptive field, enforced compatibility among adjacent blocks, and efficient deblocking. Extensive experiments demonstrate that our EWARN outperforms several state-of-the-art methods quantitatively and qualitatively with relatively small model size and less running time, achieving a good trade-off between performance and complexity.     

Feature selection methods for root-cause analysis among top-level product attributes

Manufacturing companies not only strive to deliver flawless products but also monitor product failures in the field to identify potential quality issues. When product failures occur, quality engineers must identify the root cause to improve any affected product and process. This root-cause analysis can be supported by feature selection methods that identify relevant product attributes, such as manufacturing dates with an increased number of product failures. In this paper, we present different methods for feature selection and evaluate their ability to identify relevant product attributes in a root-cause analysis. First, we compile a list of feature selection methods. Then, we summarize the properties of product attributes in warranty case data and discuss these properties regarding the challenges they pose for machine learning algorithms. Next, we simulate datasets of warranty cases, which emulate these product properties. Finally, we compare the feature selection methods based on these simulated datasets. In the end, the univariate filter information gain is determined to be a suitable method for a wide range of applications. The comparison based on simulated data provides a more general result than other publications, which only focus on a single use case. Due to the generic nature of the simulated datasets, the results can be applied to various root-cause analysis processes in different quality management applications and provide a guideline for readers who wish to explore machine learning methods for their analysis of quality data.     

Learning shape and texture progression for young child face aging

Face aging (FA) for young faces refers to rendering the aging faces at target age for an individual, generally under 20s, which is an important topic of facial age analysis. Unlike traditional FA for adults, it is challenging to age children with one deep learning-based FA network, since there are deformations of facial shapes and variations of textural details. To alleviate the deficiency, a unified FA framework for young faces is proposed, which consists of two decoupled networks to apply aging image translation. It explicitly models transformations of geometry and appearance using two components: GD-GAN, which simulates the Geometric Deformation using Generative Adversarial Network; TV-GAN, which simulates the Textural Variations guided by the age-related saliency map. Extensive experiments demonstrate that our method has advantages over the state-of-the-art methods in terms of synthesizing visually plausible images for young faces, as well as preserving the personalized features.     

A comprehensive survey on computer vision based concepts,methodologies, analysis and applications for automatic gun/knife detection

The ability to detect gun and gun held in hand or other body parts is a typical human skill. The same problem presents an imperative task for computer vision system. Automatic observer independent detection of hand held gun or gun held in the other body part, whether it is visible or concealed, provides enhance security in vulnerable places and initiates appropriate action there. Compare to the automatic object detection systems, automatic detection of gun has very few successful attempts. In the present scope of this paper, we present an extensive survey on automatic detection of gun and define a taxonomy for this particular detection system. We also describe the inherent difficulties related with this problem. In this survey of published papers, we examine different approaches used in state-of-the-art attempts and compare performances of these approaches. Finally, this paper concludes pointing to the possible research gaps in related fields.     

Secure image encryption scheme using 4D-Hyperchaotic systems based reconfigurable pseudo-random number generator and S-Box

This paper introduces the design of a hardware efficient reconfigurable pseudorandom number generator (PRNG) using two different feedback controllers based four-dimensional (4D) hyperchaotic systems i.e. Hyperchaotic-1 and -2 to provide confidentiality for digital images. The parameter's value of these two hyperchaotic systems is set to be a specific value to get the benefits i.e. all the multiplications (except a few multiplications) are performed using hardwired shifting operations rather than the binary multiplications, which doesn't utilize any hardware resource. The ordinary differential equations (ODEs) of these two systems have been exploited to build a generic architecture that fits in a single architecture. The proposed architecture provides an opportunity to switch between two different 4D hyperchaotic systems depending on the required behavior. To ensure the security strength, that can be also used in the encryption process in which encrypt the input data up to two times successively, each time using a different PRNG configuration. The proposed reconfigurable PRNG has been designed using Verilog HDL, synthesized on the Xilinx tool using the Virtex-5 (XC5VLX50T) and Zynq (XC7Z045) FPGA, its analysis has been done using Matlab tool. It has been found that the proposed architecture of PRNG has the best hardware performance and good statistical properties as it passes all fifteen NIST statistical benchmark tests while it can operate at 79.101-MHz or 1898.424-Mbps and utilize only 0.036 %, 0.23 %, and 1.77 % from the Zynq (XC7Z045) FPGA's slice registers, slice LUTs, and DSP blocks respectively. Utilizing these PRNGs, we design two 16 × 16 substitution boxes (S-boxes). The proposed S-boxes fulfill the following criteria: Bijective, Balanced, Non-linearity, Dynamic Distance, Strict Avalanche Criterion (SAC) and BIC non-linearity criterion. To demonstrate these PRNGs and S-boxes, a new three different scheme of image encryption algorithms have been developed: a) Encryption using S-box-1, b) Encryption using S-box-2 and, c) Two times encryption using S-box-1 and S-box-2. To demonstrate that the proposed cryptosystem is highly secure, we perform the security analysis (in terms of the correlation coefficient, key space, NPCR, UACI, information entropy and image encryption quantitatively in terms of (MSE, PSNR and SSIM)).     

Organic mesh template-based laminated object manufacturing to fabricate ceramics with regular micron scaled pore structures

A new aqueous slurry-based laminated object manufacturing process for porous ceramics is proposed: firstly, an organic mesh sheet is pre-paved as a pore-forming template before slurry layer scraping; secondly, the 2D pattern is built with laser outline cutting of the dried mesh–ceramic composite layer; finally, the pore structure is formed after degreasing and sintering. Alumina parts with porosities of 51.5 %, round hole diameters of 80 ± 5 μm were fabricated using 70 wt. % solid content slurry and 100 mesh nylon net. Using an organic mesh as the framework and template not only reduces the risk of damage of the green body but also ensures the regularity, uniformity and connectivity of the micron scaled pore network. The layer-by-layer drying method avoids the delamination phenomenon and improves the paving density. The new method can realize the flexible design of the pore structure by using various organic mesh templates.     

A novel fusion paradigm for multi-channel image denoising

Multi-channel and single-channel image denoising are on two important development fronts. Integrating multi-channel and single-channel image denoisers for further improvement is a valuable research direction. A natural assumption is that using more useful information is helpful to the output results. In this paper, a novel multi-channel and single-channel fusion paradigm (MSF) is proposed. The proposed MSF works by fusing the estimates of a multi-channel image denoiser and a single-channel image denoiser. The performance of recent multi-channel image denoising methods involved in the proposed MSF can be further improved at low additional time-consuming cost. Specifically, the validity principle of the proposed MSF is that the fused single-channel image denoiser can produce auxiliary estimate for the involved multi-channel image denoiser in a designed underdetermined transform domain. Based on the underdetermined transformation, we create a corresponding orthogonal transformation for fusion and better restore the multi-channel images. The quantitative and visual comparison results demonstrate that the proposed MSF can be effectively applied to several state-of-the-art multi-channel image denoising methods.