the proceedings contain 10 papers. the special focus in this conference is on computervision Applications. the topics include: AECNN: Autoencoder with Convolutional Neural Network for Hyperspectral image Classificati...
ISBN:
(纸本)9789811513862
the proceedings contain 10 papers. the special focus in this conference is on computervision Applications. the topics include: AECNN: Autoencoder with Convolutional Neural Network for Hyperspectral image Classification;optic Disc Segmentation in Fundus images Using Anatomical Atlases with Nonrigid Registration;bird Species Classification Using Transfer Learning with Multistage Training;a Deep Learning Paradigm for Automated Face Attendance;Robust Detection of Iris Region Using an Adapted SSD Framework;dynamic image Networks for Human Fall Detection in 360-degree Videos;image Segmentation and Geometric Feature Based Approach for Fast Video Summarization of Surveillance Videos;supervised Hashing for Retrieval of Multimodal Biometric Data.
We present a novel algorithm to remove near regular, fence or wire like foreground patterns from an image. the fence detection or fence removal algorithms, developed so far, have poor performance in detecting the fenc...
详细信息
ISBN:
(纸本)9781450347532
We present a novel algorithm to remove near regular, fence or wire like foreground patterns from an image. the fence detection or fence removal algorithms, developed so far, have poor performance in detecting the fence. We use signal demixing to utilize the sparsity and regularity property of fences to detect them. Results demonstrate the effectiveness of our technique as compared to other state of the art techniques.
Dictionary learning has been used to solve inverse problems in imaging and as an unsupervised feature extraction tool in vision. the main disadvantage of dictionary learning for applications in vision is the relativel...
详细信息
ISBN:
(纸本)9781450347532
Dictionary learning has been used to solve inverse problems in imaging and as an unsupervised feature extraction tool in vision. the main disadvantage of dictionary learning for applications in vision is the relatively long feature extraction time during testing;owing to the requirement of solving an iterative optimization problem (10-minimization). the newly developed analysis framework of transform learning does not suffer from this shortcoming;feature extraction only requires a matrix vector multiplication. this work proposes an alternate formulation for transform learning that improves the accuracy even further. Experiments on benchmark databases show that our proposed transform learning yields results better than dictionary learning, autoencoder (AE) and restricted Boltzmann machine (RBM). the feature extraction time is fast as AE and RBM.
Music transcription refers to the process of analyzing a piece of music to generate a sequence of constituent notes and their duration. Transcription of music from audio signals is fraught with problems due to auditor...
详细信息
ISBN:
(纸本)9781450347532
Music transcription refers to the process of analyzing a piece of music to generate a sequence of constituent notes and their duration. Transcription of music from audio signals is fraught with problems due to auditory interference such as ambient noise, multiple instruments playing simultaneously, accompanying vocals or polyphonic sounds. For several instruments, there exists added information for music transcription which can be derived from a video sequence of the instrument as it is being played. this paper proposes a method to utilize this visual information for the case of keyboard-like instruments to generate a transcript automatically, by analyzing the video frames. We present encouraging results under varying lighting conditions on different song sequences played out on a keyboard.
Understanding crowd dynamics is an interesting problem in computervision owing to its various applications. We propose a dynamical system to model the dynamics of collective motion of the crowd. the model learns the ...
详细信息
ISBN:
(纸本)9781450347532
Understanding crowd dynamics is an interesting problem in computervision owing to its various applications. We propose a dynamical system to model the dynamics of collective motion of the crowd. the model learns the spatio-temporal interaction pattern of the crowd from the track data captured over a time period. the model is trained under a least square formulation with spatial and temporal constraints. the spatial constraint allows the model to consider only the neighbors of a particular agent and the temporal constraint enforces temporal smoothness in the model. We also propose an effective group detection algorithm that utilizes the eigenvectors of the interaction matrix of the model. the group detection is cast as a spectral clustering problem. Extensive experimentation demonstrates a superlative performance of our group detection algorithm over state-of-the-art methods.
image Hallucination has many applications in areas such as imageprocessing, computational photography and image fusion. In this paper, we present an image Hallucination technique based on the template (patch) matchin...
详细信息
ISBN:
(纸本)9781450347532
image Hallucination has many applications in areas such as imageprocessing, computational photography and image fusion. In this paper, we present an image Hallucination technique based on the template (patch) matching from the database of time lapse images and learned locally affine model. Template based techniques suffer from blocky artifacts. So, we propose two approaches for imposing consistency criteria across neighbouring patches in the form of regularization. We validate our Color transfer technique by hallucinating a variety of natural images at different times the day. We compare the proposed approach with other state of the art techniques of example image based color transfer and show that the images obtained using our approach look more plausible and natural.
Virtual garments like shirts and trousers are created from 2D patterns stitched over 3D models. However, indian garments, like dhotis and saris, pose a unique draping challenge for physically-simulated garment systems...
详细信息
ISBN:
(纸本)9781450347532
Virtual garments like shirts and trousers are created from 2D patterns stitched over 3D models. However, indian garments, like dhotis and saris, pose a unique draping challenge for physically-simulated garment systems, as they are not stitched garments. We present a method to intuitively specify the parameters governing the drape of an indian garment using a sketch-based interface. We then interpret the sketch strokes to procedural, physically-simulated draping routines to wrap, pin and tuck the garments around the body mesh as needed. After draping, the garments are ready to be simulated and used during animation as required. We present several examples of our draping technique.
One of the common image forgery techniques is the splicing, where parts from different images are copied and pasted onto a single image. this paper proposes a new forensics method for detecting splicing forgeries in i...
详细信息
ISBN:
(纸本)9781450347532
One of the common image forgery techniques is the splicing, where parts from different images are copied and pasted onto a single image. this paper proposes a new forensics method for detecting splicing forgeries in images containing human faces. Our approach is based on extracting an illumination-signature from the faces of people present in an image using the dichromatic reflection model (DRM). the dichromatic plane histogram (DPH), which is calculated by applying the 2D Hough Transform on the face images, is used as the illumination-signature. the correlation measure is employed to compute the similarity between the DPHs obtained from different faces present in an image. Finally, a simple threshold on this similarity measure exposes splicing forgeries in the image. Experimental results show the efficacy of the proposed method.
Manual analysis of pedestrians for surveillance of large crowds in real time applications is not practical. Tracking-Learning-Detection suggested by Kalal , Mikolajczyk and Matas [1] is one of the most prominent autom...
详细信息
ISBN:
(纸本)9781450347532
Manual analysis of pedestrians for surveillance of large crowds in real time applications is not practical. Tracking-Learning-Detection suggested by Kalal , Mikolajczyk and Matas [1] is one of the most prominent automatic object tracking system. TLD can track single object and can handle occlusion and appearance change but it suffers from limitations .In this paper, tracking of multiple objects and estimation of their trajectory is suggested using improved TLD. Feature tracking is suggested in place of grid based tracking to solve the limitation of tracking during out of plane rotation .this also leads to optimization of algorithm. Proposed algorithm also achieves auto-initialization with detection of pedestrians in the first frame which makes it suitable for real time pedestrian tracking.
Skin colour detection under poor or varying illumination condition is a big challenge for various imageprocessing and human-computer interaction applications. In this paper, a novel skin detection method utilizing im...
详细信息
ISBN:
(纸本)9781450347532
Skin colour detection under poor or varying illumination condition is a big challenge for various imageprocessing and human-computer interaction applications. In this paper, a novel skin detection method utilizing image pixel distribution in a given colour space is proposed. the pixel distribution of an image can provide a better localization of the actual skin colour distribution of an image. Hence, a local skin distribution model (LSDM) is derived using the image pixel distribution model and its similarity withthe global skin distribution model (GSDM). Finally, a fusion-based skin model is obtained using boththe GSDM and the LSDM. Subsequently, a dynamic region growing method is employed to improve the overall detection rate. Experimental results show that proposed skin detection method can significantly improve the detection accuracy in presence of varying illumination conditions.
暂无评论