Dense depth maps play an important role in computervision and AR (Augmented Reality). For CV applications, a dense depth map is the cornerstone of 3D reconstruction allowing real objects to be precisely displayed in ...
详细信息
ISBN:
(纸本)9781728188089
Dense depth maps play an important role in computervision and AR (Augmented Reality). For CV applications, a dense depth map is the cornerstone of 3D reconstruction allowing real objects to be precisely displayed in the computer. And Dense depth maps can handle correct occlusion relationships between virtual content and real objects for better user experience in AR. However, the complicated computation limits the development of computing dense depth maps. We present a novel algorithm that produces low latency, spatio-temporally smooth dense depth maps using only a CPU. the depth maps exhibit sharp discontinuities at depth edges in low computational complexity ways. Our algorithm obtains the sparse SLAM reconstruction first, then extracts coarse depth edges from a down-sampled RGB image by morphology operations. Next, we thin the depth edges and align them with image edges. Finally, an effective initialization scheme and an improved optimization solver are adopted to accelerate convergence. We evaluate our proposal quantitatively and the result shows improvements on the accuracy of depth map with respect to other state-of-the-art and baseline techniques.
Currently, iris identification systems are not easy to use since they need a strict cooperation of the user during the snapshot acquisition process. Several acquisitions are generally needed to obtain a workable image...
详细信息
ISBN:
(纸本)354029032X
Currently, iris identification systems are not easy to use since they need a strict cooperation of the user during the snapshot acquisition process. Several acquisitions are generally needed to obtain a workable image of the iris for recognition purpose. To make the system more flexible and open to large public applications, we propose to work on the entire sequence acquired by a camera during the enrolment. Hence the recognition step can be applied on a selected number of the "best workable images" of the iris within the sequence. In this context, the aim of the paper is to present a method for pupil tracking based on a dynamic Gaussian Mixture Model (GMM) together with Kalman prediction of the pupil position along the sequence. the method has been experimented on a real video sequence captured by a near Infra-Red (IR) sensitive camera and has shown its effectiveness in nearly real time computing.
this paper is concerned with an accurate and efficient fingerprint matching method. We have two main contributions: 1. we define a novel feature vector for each fingerprint minutia based on the global orientation fiel...
详细信息
ISBN:
(纸本)0769522718
this paper is concerned with an accurate and efficient fingerprint matching method. We have two main contributions: 1. we define a novel feature vector for each fingerprint minutia based on the global orientation field estimated from the fingerprint impression. these features are used to identify corresponding minutiae between two fingerprint impressions by computing the Euclidean distance between these feature vectors. 2. a novel distortion-tolerant matching algorithm based on the closest triangle is developed. Furthermore, the fingerprint directional field is also used to compute the final matching score combining with minutiae elaborately. A series of experiments conducted on the public data collection, FVC2002 DB3 set A (800 fingerprints), demonstrates the effectiveness of our method.
In this paper we compare different ways of representing the photometric changes in image intensities caused by changes in illumination and viewpoint, aiming at a balance between goodness-of-fit and low complexity. We ...
详细信息
the detection and recognition of handwritten arithmetic expressions (AEs) play an important role in document retrieval [ 21] and analysis. they are very difficult because of the structural complexity and the variabili...
详细信息
ISBN:
(纸本)9783030880040;9783030880033
the detection and recognition of handwritten arithmetic expressions (AEs) play an important role in document retrieval [ 21] and analysis. they are very difficult because of the structural complexity and the variability of appearance. In this paper, we propose a novel framework to detect and recognize AEs in an End-to-End manner. Firstly, an AE detector based on EfficientNet-B1 [17] is designed to locate all AE instances efficiently. Upon AE location, the RoI Rotate module [11] is adopted to transform visual features for AE proposals. the transformed features are then fed into an attention mechanism based recognizer for AE recognition. the whole network for detection and recognition is trained End-to-End on document images annotated AE locations and transcripts. Since the datasets in this field are rare, we also construct a dataset named HAED, which contains 1069 images (855 for training, and 214 for testing). Extensive experiments on two datasets (HAED and TFD-ICDAR 2019) show that the proposed method has achieved competitive performance on both datasets.
Facial expression recognition is a challenging task in computervision field using only single facial image. As we know, human faces are convex spheres. the self-occlusion phenomenon generated from face pose will seri...
详细信息
ISBN:
(纸本)9781538637883
Facial expression recognition is a challenging task in computervision field using only single facial image. As we know, human faces are convex spheres. the self-occlusion phenomenon generated from face pose will seriously affect the accuracy of expression recognition. In order to solve this problem, we propose a novel facial expression recognition method for different pose faces based on special landmark detection (FER-MPI-SFL). Our method is based on two shared networks. the outputs of the first Network are 29 special landmarks and 1 face box, which are the inputs of the second network and used to estimate face pose. the methods of RoIAlign and feature map concatenation are introduced in the second network to recognize the facial expression. the weight allocation of feature maps concatenation is guided by the result of pose estimation. In addition, an improved center loss is proposed to make the distances between the features of different expressions larger and easier to be classified in the feature space. As a result, superior performance to other state-of-the-art methods is achieved in facial expression databases CK+, MMI, Oulu-CASIA VIS and a new created database CASIA-MFE which contains more faces with different poses.
this book constitutes the refereed proceedings of the 10thchineseconference on Advances in Image and Graphics Technologies, IGTA 2015, held in Beijing, China, in June 2015. the 50 papers presented were carefully rev...
ISBN:
(数字)9783662477915
ISBN:
(纸本)9783662477908;9783662477915
this book constitutes the refereed proceedings of the 10thchineseconference on Advances in Image and Graphics Technologies, IGTA 2015, held in Beijing, China, in June 2015. the 50 papers presented were carefully reviewed and selected from 138 submissions. they provide a forum for sharing new aspects of the progresses in the areas of image processing technology, image analysis und understanding, computervision and patternrecognition, big data mining, computer graphics and VR, image technology application.
Learning depth from a single image is an important issue in computervision. To solve this problem, encoder-decoder architect is usually employed as a powerful architecture to learn the dense corresponding function. I...
详细信息
ISBN:
(纸本)9781538637883
Learning depth from a single image is an important issue in computervision. To solve this problem, encoder-decoder architect is usually employed as a powerful architecture to learn the dense corresponding function. In this work, we propose a symmetrical Spindle network of the encoder-decoder to learn the fine-grained depth. Unlike traditional convolution neural network, we first boost up the feature maps from low-dimension space to a high-dimension space, then extract the features for monocular depth learning. In order to overcome limitation of the computer memory, a single image super-resolution technique is proposed to replace the boosting process by fusing local cues in edge direction. Given the super-resolution images, the monocular depth learning needs more global information than most architectures for pixel-wise predictions. To address this issue, dilation kernel method is proposed to enlarge the receptive field in each layer. For the task of the super-resolution, the proposed method achieves better performance than the state-of-the-art methods. Extensive experiments on the monocular depth inference demonstrate that the Spindle network could achieve comparable performance on the NYU and Make3D datasets, compared withthe state-of-the-art algorithms. the proposed method reveals a new perspective to learn the depth from a single image, which shows a promising generality to other pixel-wise prediction problems.
Ellipses are important elements in projective geometry. Accurate extraction of ellipse information is the first step in many computervision applications, such as ellipse-based camera calibration and camera pose estim...
详细信息
ISBN:
(数字)9781665490627
ISBN:
(纸本)9781665490627
Ellipses are important elements in projective geometry. Accurate extraction of ellipse information is the first step in many computervision applications, such as ellipse-based camera calibration and camera pose estimation. At present, most ellipse detection algorithms rely on the edge features extracted by Canny, which leads to a number of wrong detection results since non-ellipse edges features are also involved. To address this problem, this paper proposes a novel ellipse marker detection neural network, called EllipseNet. Notably, we propose a new loss function to enhance the rotation perception ability of EllipseNet. Furthermore, a novel ellipse marker data enhancement method is proposed for saving the time cost of labelling ellipse parameters. Experiments show that EllipseNet can improve the detection precision of ellipse regions by more than 3% improvement compared with other SOTA general object detectors.
暂无评论