This paper proposes a psychologically inspired convolutional neural network (PI-CNN) to achieve automatic facial beauty prediction. Different from the previous methods, PI-CNN is hierarchical model that facilitates both representation learning and predictor training. Inspired by recent psychological studies, significant appearance features of detail, lighting color were used optimize using new cascaded fine-tuning method. Experiments indicate fine-tuned robust variances, obtains highest...

An open research problem in automatic signature verification is the skilled forgery attacks. However, forgeries are very difficult to acquire for representation learning. To tackle this issue, paper proposes learn dynamic representations through ranking synthesized signatures. First, a neuromotor inspired synthesis method proposed synthesize signatures with different distortion levels any template signature. Then, given templates, we construct lightweight one-dimensional convolutional...

Beauty is a universal concept which has long been explored by philosophers, artists and psychologists, but there are few implementations of automated facial beauty assessment in computational science. In this paper, we develop an Chinese female classification system through the application machine learning algorithm SVM (Support Vector Machine). We present simple effective feature extraction for classification. 17 geometric features designed to abstractly represent each image. The experiment...

Human skeleton contains significant information about actions, therefore, it is quite intuitive to incorporate skeletons in human action recognition. resembles a graph where body joints and bones mimic nodes edges. This resemblance of structure the main motivation apply convolutional neural network for Results show that discriminant contribution different not equal actions. Therefore, we propose use attention-joints correspond significantly contributing specific Features corresponding only...

Fog computing has recently emerged as an extension of cloud in providing high-performance services for delay-sensitive Internet Things (IoT) applications. By offloading tasks to a geographically proximal fog server instead remote cloud, the delay performance can be greatly improved. However, some IoT applications may still experience considerable delays, including queuing and computation when huge amounts instantaneously feed into resource-limited node. Accordingly, cooperation among close...

In this paper, we present an effective method to analyze the recognition confidence of handwritten Chinese character, based on softmax regression score a high performance convolutional neural network (CNN). Through careful and thorough statistics 827,685 testing samples that randomly selected from total 8836 different classes characters, find measurement CNN is useful metric know how reliable results are. Furthermore, by experiments can be used out similar confusable character-pairs, check...

Recently, deep learning has greatly promoted the performance of license plate recognition (LPR) by robust features from numerous labeled data. However, large variation wild plates across complicated environments and perspectives is still a huge challenge to LPR. To solve problem, we propose an effective efficient shared adversarial training network (SATN) in this paper, which can learn environment-independent perspective-free semantic with prior knowledge standard stencil-rendered plates, as...

Beauty is an abstract concept that inherently difficult to quantify and evaluate. The analysis of facial attractiveness has received much research attention in the past. Recent work shown can be learned by machine, using supervised learning techniques. This paper proposes a computational method for estimating based on Gabor features support vector machine (SVM). We conducted several experiments different feature types including features, geometric eigenfaces. found feature-based produced...

In this paper, we propose a novel contour-based method to beautify online handwritten Chinese character the Kai style calligraphy. According feature and structure of calligraphy, Bezier curve is used sketch user-input stroke segment contour corner contour. We get whole path beautified by connecting segments' corners' end-to-end. Anti-aliasing technology make edge fine smooth. Finally, path-fill algorithm adopted fill inner Our system proved be effective efficient. Meanwhile, users can choose...

In this paper, we present an effective method to analyze the recognition confidence of handwritten Chinese character, based on softmax regression score a high performance convolutional neural networks (CNN). Through careful and thorough statistics 827,685 testing samples that randomly selected from total 8836 different classes characters, find measurement CNN is useful metric know how reliable results are. Furthermore, by experiments can be used out similar confusable character-pairs, check...

An open research problem in automatic signature verification is the skilled forgery attacks. However, forgeries are very difficult to acquire for representation learning. To tackle this issue, paper proposes learn dynamic representations through ranking synthesized signatures. First, a neuromotor inspired synthesis method proposed synthesize signatures with different distortion levels any template signature. Then, given templates, we construct lightweight one-dimensional convolutional...