一种有选择的图像灰度化方法

提出了一种对彩色图像进行有选择灰度化的方法，并采用Matlab实现了该算法。该方法可以将选中的任意颜色灰度化为黑色，而与该颜色距离越远的颜色，其灰度值越高。利用该方法可以较好地提取出彩色图像中不同颜色所反映的信息，便于基于颜色的图像信息传输和处理。     

Scene graph generation by multi-level semantic tasks

Understanding scene image includes detecting and recognizing objects, estimating the interaction relationships of the detected objects, and describing image regions with sentences. However, since the complexity and variety of scene image, existing methods take object detection or vision relationship estimate as the research targets in scene understanding, and the obtained results are not satisfactory. In this work, we propose a Multi-level Semantic Tasks Generation Network (MSTG) to leverage mutual connections across object detection, visual relationship detection and image captioning, to solve jointly and improve the accuracy of the three vision tasks and achieve the more comprehensive and accurate understanding of scene image. The model uses a message pass graph to mutual connections and iterative updates across the different semantic features to improve the accuracy of scene graph generation, and introduces a fused attention mechanism to improve the accuracy of image captioning while using the mutual connections and refines of different semantic features to improve the accuracy of object detection and scene graph generation. Experiments on Visual Genome and COCO datasets indicate that the proposed method can jointly learn the three vision tasks to improve the accuracy of those visual tasks generation.

     

融合深层特征与边缘特征的皮肤检测校正算法

当皮肤区域与非皮肤区域没有明显边界时, 皮肤检测变得更加困难. 针对这一问题, 本文提出了一种新的皮肤检测校正算法. 本文首先利用卷积神经网络分级对皮肤的颜色、纹理等特征进行提取, 通过门控卷积层对皮肤与非皮肤像素的边界区域进行细化, 以增强皮肤检测的效果, 最后利用ASPP将深层信息与边缘信息进行融合. 本文将经过阈值粗分割的检测结果作为输入, 在ECU和Pratheepan两个数据集上进行了评估, 实验结果表明, 本算法在ECU数据集上的准确率达到了91%, 在Pratheepan数据集的准确率达到了95%, 与现有方法相比, 本文算法的性能有明显的提升.     

Robust artifact-free high dynamic range imaging of dynamic scenes

The irradiance range of the real-world scene is often beyond the capability of digital cameras. Therefore, High Dynamic Range (HDR) images can be generated by fusing images with different exposure of the same scene. However, moving objects pose the most severe problem in the HDR imaging, leading to the annoying ghost artifacts in the fused image. In this paper, we present a novel HDR technique to address the moving objects problem. Since the input low dynamic range (LDR) images captured by a camera act as static linear related backgrounds with moving objects during each individual exposures, we formulate the detection of foreground moving objects as a rank minimization problem. Meanwhile, in order to eliminate the image blurring caused by background slightly change of LDR images, we further rectify the background by employing the irradiances alignment. Experiments on image sequences show that the proposed algorithm performs significant gains in synthesized HDR image quality compare to state-of-the-art methods.

     

Image classification without segmentation using a hybrid pyramid kernel

Image classification usually requires complicated segmentation to separate foreground objects from the background scene. However, the statistical content of a background scene can actually provide very useful information for classification. In this paper, we propose a new hybrid pyramid kernel which incorporates local features extracted from both dense regular grids and interest points for image classification, without requiring segmentation. Features extracted from dense regular grids can better capture information about the background scene, while interest points detected at corners and edges can better capture information about the salient objects. In our algorithm, these two local features are combined in both the spatial and the feature-space domains, and are organized into pyramid representations. In order to obtain better classification accuracy, we fine-tune the parameters involved in the similarity measure, and we determine discriminative regions by means of relevance feedback. From the experimental results, we observe that our algorithm can achieve a 6.37 % increase in performance as compared to other pyramid-representation-based methods. To evaluate the applicability of the proposed hybrid kernel to large-scale databases, we have performed a cross-dataset experiment and investigated the effect of foreground/background features on each of the kernels. In particular, the proposed hybrid kernel has been proven to satisfy Mercer’s condition and is efficient in measuring the similarity between image features. For instance, the computational complexity of the proposed hybrid kernel is proportional to the number of features.     

Face detection based on skin color likelihood

We propose a face detection method based on skin color likelihood via a boosting algorithm which emphasizes skin color information while deemphasizing non-skin color information. A stochastic model is adapted to compute the similarity between a color region and the skin color. Both Haar-like features and Local Binary Pattern (LBP) features are utilized to build a cascaded classifier. The boosted classifier is implemented based on skin color emphasis to localize the face region from a color image. Based on our experiments, the proposed method shows good tolerance to face pose variation and complex background with significant improvements over classical boosting-based classifiers in terms of total error rate performance.     

结合肤色分割与平滑的人脸图像快速美化

目的 针对目前人脸图像美化算法存在的对于细节丰富的眼睛和头发等区域处理过度平滑,美化后的图像整体美化效果较差等问题,提出一种基于肤色分割与平滑人脸图像的美化方法。方法 首先对脸部瑕疵特性,用双指数边缘保护滤波器平滑人脸图像的瑕疵,与此同时很好保持图像边缘信息;再通过利用色度直方图自适应快速检测、修正、分割肤色区域;然后利用拟合高斯羽化皮肤区域生成蒙版,融合平滑图像和原图像,保留图像头发背景等细节信息;最后基于人像美感标准,对皮肤亮度通过拟合log曲线实现快速自适应调整人脸图像亮度,增强眼睛等细节,从而快速实现人脸图像美化方法。结果 通过与其他人像美化算法相比较,在保留边缘方面,该算法更有效地对皮肤边缘上的瑕疵进行平滑,达到更好地美化人脸图像;而在时间复杂度方面,相对于前人的算法,计算速度快12倍,实现快速美化人脸图像。结论 该算法适应能力较强,对大部分人脸图像的脸部瑕疵完美去除的同时达到背景信息不变,肤色美白自然,使整体美化效果显著;尤其是细节丰富的边缘区域平滑适度,具有一定的实用性。     

一种基于多层语义特征的图像理解方法

视觉场景理解包括检测和识别物体、推理被检测物体之间的视觉关系以及使用语句描述图像区域.为了实现对场景图像更全面、更准确的理解,将物体检测、视觉关系检测和图像描述视为场景理解中3种不同语义层次的视觉任务,提出一种基于多层语义特征的图像理解模型,并将这3种不同语义层进行相互连接以共同解决场景理解任务.该模型通过一个信息传递图将物体、关系短语和图像描述的语义特征同时进行迭代和更新,更新后的语义特征被用于分类物体和视觉关系、生成场景图和描述,并引入融合注意力机制以提升描述的准确性.在视觉基因组和COCO数据集上的实验结果表明,所提出的方法在场景图生成和图像描述任务上拥有比现有方法更好的性能.     

Hybrid Human Skin Detection Using Neural Network and K-Means Clustering Technique

Human skin detection is an essential step in most human detection applications, such as face detection. The performance of any skin detection system depends on assessment of two components: feature extraction and detection method. Skin color is a robust cue used for human skin detection. However, the performance of color-based detection methods is constrained by the overlapping color spaces of skin and non-skin pixels. To increase the accuracy of skin detection, texture features can be exploited as additional cues. In this paper, we propose a hybrid skin detection method based on YIQ color space and the statistical features of skin. A Multilayer Perceptron artificial neural network, which is a universal classifier, is combined with the k-means clustering method to accurately detect skin. The experimental results show that the proposed method can achieve high accuracy with an F₁-measure of 87.82% based on images from the ECU database.     

基于颜色和纹理的皮肤检测方法

提出一种新的基于颜色和纹理特征的皮肤检测方法,应用JSEG算法将图像分割成任意形状的相似图像区域集,然后从中提取颜色特征和纹理特征,最后应用高斯混合模型（Gaussian Mixture Model,GMM）,并根据一定的判断准则（综合考虑颜色特征和纹理特征）进行皮肤和非皮肤区域分类．     

Active Foreground Region Extraction and Tracking for Sports Video Annotation

Automatic video segmentation plays a vital role in sports videos annotation. This paper presents a fully automatic and computationally efficient algorithm for analysis of sports videos. Various methods of automatic shot boundary detection have been proposed to perform automatic video segmentation. These investigations mainly concentrate on detecting fades and dissolves for fast processing of the entire video scene without providing any additional feedback on object relativity within the shots. The goal of the proposed method is to identify regions that perform certain activities in a scene. The model uses some low-level feature video processing algorithms to extract the shot boundaries from a video scene and to identify dominant colours within these boundaries. An object classification method is used for clustering the seed distributions of the dominant colours to homogeneous regions. Using a simple tracking method a classification of these regions to active or static is performed. The efficiency of the proposed framework is demonstrated over a standard video benchmark with numerous types of sport events and the experimental results show that our algorithm can be used with high accuracy for automatic annotation of active regions for sport videos.     

基于帧间差分的自适应运动目标检测方法*

本文提出了一种基于帧间差分的自适应运动目标检测算法。算法利用直方图统计各像素点处最大概率灰度的方法提取出连续视频的背景图像;相邻帧利用帧差法得到运动区域图像;利用运动区域图像与背景图像差分的方法提取出运动目标。实验结果表明,该算法能在多个不确定性因素的序列视频中较好的提取背景图像,能及时响应实际场景变化,提高运动目标检测的质量。     

A comprehensive system for image scene classification

In recent years, image scene classification based on low/high-level features has been considered as one of the most important and challenging problems faced in image processing research. The high-level features based on semantic concepts present a more accurate and closer model to the human perception of the image scene content. This paper presents a new multi-stage approach for image scene classification based on high-level semantic features extracted from image content. In the first stage, the object boundaries and their labels that represent the content are extracted. For this purpose, a combined method of a fully convolutional deep network and a combined network of a two-class SVM-fuzzy and SVR are used. Topic modeling is used to represent the latent relationships between the objects. Hence in the second stage, a new combination of methods consisting of the bag of visual words, and supervised document neural autoregressive distribution estimator is used to extract the latent topics (topic modeling) in the image. Finally, classification based on Bayesian method is performed according to the extracted features of the deep network, objects labels and the latent topics in the image. The proposed method has been evaluated on three datasets: Scene15, UIUC Sports, and MIT-67 Indoor. The experimental results show that the proposed approach achieves average performance improvement of 12%, 11% and 14% in the accuracy of object detection, and 0.5%, 0.6% and 1.8% in the mean average precision criteria of the image scene classification, compared to the previous state-of-the-art methods on these three datasets.

     

一种基于降维的肤色特征提取和肤色检测方法

本文提出了一种综合多个颜色空间分量的肤色特征提取方法,并通过SVM分类器进行肤色和非肤色的分类,从而实现肤色检测。特征提取先后采用了PFA和KPCA算法。肤色检测的实质是肤色和非肤色分类问题。针对先前提取的特征,采用基于SVM分类器进行分类。实验结果表明,基于PFA、KPCA特征提取和SVM分类的肤色检测正确率可以达到87.76%,误判率仅为14.62%。     

Aerial image dehazing using a deep convolutional autoencoder

Aerial images and videos are extensively used for object detection and target tracking. However, due to the presence of thin clouds, haze or smoke from buildings, the processing of aerial data can be challenging. Existing single-image dehazing methods that work on ground-to-ground images, do not perform well on aerial images. Moreover, current dehazing methods are not capable for real-time processing. In this paper, a new end-to-end aerial image dehazing method using a deep convolutional autoencoder is proposed. Using the convolutional autoencoder, the dehazing problem is divided into two parts, namely, encoder, which aims extract important features to dehaze hazy regions and decoder, which aims to reconstruct the dehazed image using the down-sampled image received from the encoder. In this proposed method, we also exploit the superpixels in two different scales to generate synthetic thin cloud data to train our network. Since this network is trained in an end-to-end manner, in the test phase, for each input hazy aerial image, the proposed algorithm outputs a dehazed version without requiring any other information such as transmission map or atmospheric light value. With the proposed method, hazy regions are dehazed and objects within hazy regions become more visible while the contrast of non-hazy regions is increased. Experimental results on synthetic and real hazy aerial images demonstrate the superiority of the proposed method compared to existing dehazing methods in terms of quality and speed.

     

Human mimic color perception for segmentation of color images using a three-layered self-organizing map previously trained to classify color chromaticity

Most of the works addressing segmentation of color images use clustering-based methods; the drawback with such methods is that they require a priori knowledge of the amount of clusters, so the number of clusters is set depending on the nature of the scene so as not to lose color features of the scene. Other works that employ different unsupervised learning-based methods use the colors of the given image, but the classifying method employed is retrained again when a new image is given. Humans have the nature capability to: (1) recognize colors by using their previous knowledge, that is, they do not need to learn to identify colors every time they observe a new image and, (2) within a scene, humans can recognize regions or objects by their chromaticity features. Hence, in this paper we propose to emulate the human color perception for color image segmentation. We train a three-layered self-organizing map with chromaticity samples so that the neural network is able to segment color images by their chromaticity features. When training is finished, we use the same neural network to process several images, without training it again and without specifying, to some extent, the number of colors the image have. The hue component of colors is extracted by mapping the input image from the RGB space to the HSV space. We test our proposal using the Berkeley segmentation database and compare quantitatively our results with related works; according to the results comparison, we claim that our approach is competitive.

     

ForegroundNet：一种基于语义与动态特征的前景检测算法

针对以往的前景检测方法对场景信息依赖较多的问题,提出了一种实时的无需迭 代更新背景模型的前景检测深度学习模型ForegroundNet。ForegroundNet 首先通过骨干网络从 当前图像和辅助图像中提取语义特征,辅助图像为相邻的图像帧或者是自动生成的视频背景图 像;然后将提取得到的特征输入到包含短连接的反卷积网络中,使得最终特征图在与输入图像 具有相同的大小,并且包含不同尺度的语义及动态特征;最后使用softmax 层进行二值分类, 得到最终检测结果。在CDNet 数据集上进行的实验结果表明,相比于当前F 值为0.82 的次优 方法,ForegroundNet 能够获得0.94 的F 值,具有更高的检测精度;同时ForegroundNet 检测速 度达到123 fps,具有良好的实时性。     

各向异性导向滤波的红外与可见光图像融合

目的 针对红外与可见光图像融合时易产生边缘细节信息丢失、融合结果有光晕伪影等问题，同时为充分获取多源图像的重要特征，将各向异性导向滤波和相位一致性结合，提出一种红外与可见光图像融合算法。方法 首先，采用各向异性导向滤波从源图像获得包含大尺度变化的基础图和包含小尺度细节的系列细节图；其次，利用相位一致性和高斯滤波计算显著图，进而通过对比像素显著性得到初始权重二值图，再利用各向异性导向滤波优化权重图，达到去除噪声和抑制光晕伪影；最后，通过图像重构得到融合结果。结果 从主客观两个方面，将所提方法与卷积神经网络（convolutional neural network，CNN）、双树复小波变换（dual-tree complex wavelet transform，DTCWT）、导向滤波（guided filtering，GFF）和各向异性扩散（anisotropic diffusion，ADF）等4种经典红外与可见光融合方法在TNO公开数据集上进行实验对比。主观分析上，所提算法结果在边缘细节、背景保存和目标完整度等方面均优于其他4种方法；客观分析上，选取互信息（mutual information，MI）、边缘信息保持度（degree of edge information，Q^AB/F）、熵（entropy，EN）和基于梯度的特征互信息（gradient based feature mutual information，FMI_gradient）等4种图像质量评价指数进行综合评价。相较于其他4种方法，本文算法的各项指标均有一定幅度的提高，MI平均值较GFF提高了21.67%，Q^AB/F平均值较CNN提高了20.21%，EN平均值较CNN提高了5.69%，FMI_gradient平均值较GFF提高了3.14%。结论 本文基于各向异性导向滤波融合算法可解决原始导向滤波存在的细节"光晕"问题，有效抑制融合结果中伪影的产生，同时具有尺度感知特性，能更好保留源图像的边缘细节信息和背景信息，提高了融合结果的准确性。     

Saliency detection via image sparse representation and color features combination

Saliency detection is a technique to analyze image surroundings to extract relevant regions from the background. In this paper, we propose a simple and effective saliency detection method based on image sparse representation and color features combination. First, the input image is segmented into non-overlapping super-pixels, so as to perform the saliency detection at the region level to reduce computational complexity. Then, a background optimization selection scheme is used to construct an appropriate background template. Based on this, a primary saliency map is obtained by using image sparse representation. Next, through the linear combination of color coefficients we generate an improved saliency map with more prominent salient regions. Finally, the two saliency maps are integrated within Bayesian framework to obtain the final saliency map. Experimental results show that the proposed method has desirable detection performance in terms of detection accuracy and running time.

     

Robust lip region segmentation for lip images with complex background

Robust and accurate lip region segmentation is of vital importance for lip image analysis. However, most of the current techniques break down in the presence of mustaches and beards. With mustaches and beards, the background region becomes complex and inhomogeneous. We propose in this paper a novel multi-class, shape-guided FCM (MS-FCM) clustering algorithm to solve this problem. For this new approach, one cluster is set for the object, i.e. the lip region, and a combination of multiple clusters for the background which generally includes the skin region, lip shadow or beards. The proper number of background clusters is derived automatically which maximizes a cluster validity index. A spatial penalty term considering the spatial location information is introduced and incorporated into the objective function such that pixels having similar color but located in different regions can be differentiated. This facilitates the separation of lip and background pixels that otherwise are inseparable due to the similarity in color. Experimental results show that the proposed algorithm provides accurate lip-background partition even for the images with complex background features like mustaches and beards.