Our framework relies on the user providing an initial estimate of the depth, where the user marks objects and regions as closer or farther from the camera. We allow the user to mark with monochromatic intensities, as well as a varying color palette from dark to light, serving in the same function as the intensities. […]
PAIRWISE CONSTRAINTS FOR ACCELERATED LEARNING-BASED INTERACTIVE IMAGE SEGMENTATION
Image segmentation refers to the task of grouping image pixels into a meaningful partition such that pixels falling in the same group are similar to each other, and different than those in other groups, in terms of a perceptually meaningful similarity measure. Segmentation often is used as a pre-processing step before higher level image processing […]
INTERACTIVE IMAGE SEGMENTATION BASED ON ACCELERATED LEARNING USING PAIRWISE CONSTRAINTS
Segmentation often is used as a pre-processing step before higher level image processing or understanding. Manually segmenting images can be laborious and time-consuming, especially for large images, and can be prone to subjectivity. At the same time, developing a generic unsupervised segmentation algorithm that can be accurately applied to all, or even many, types of […]
SPARSE REPRESENTATION BASED FINGERPRINT COMPRESSION
Large volumes of fingerprint are collected and stored every day in a wide range of applications, including forensics and access control. Due to the large number and size of fingerprint images, data compression has to be applied to reduce the storage and communication bandwidth requirements of those images. Obtaining an over complete dictionary from a […]
A NOVEL FINGERPRINT COMPRESSION ALGORITHM BASED ON SPARSE REPRESENTATION
A new compression algorithm adapted to fingerprint images is introduced. Despite the simplicity of our proposed algorithms, they compare favorably with existing more sophisticated algorithms, especially at high compression ratios. Due to the block-by-block processing mechanism, however, the algorithm has higher complexities. The proposed method has the ability by updating the dictionary. The specific process […]
Video File Restoration Using Video Codec Specifications
This paper proposes a technique to restore the video data on a frame-by frame basis from its corrupted versions where the video data has been significantly fragmented or partly overwritten in the storage media. The proposed technique restores the video data in a frame unit, not in a file unit. The proposed method restores a […]
Foveated Video Quality Metric based on Wavelet Distortion Visibility
In this paper we propose an FR attention driven foveated video quality (AFViQ) metric. A perceptual based foveal imaging model consisting of an improved video attention model and an advanced fixation prediction approach by simulating the essential functionality of eye movement; ii) an accurate video quality metric by integrating the foveal imaging model into wavelet-based […]
A New Compression Algorithm for Fingerprint Image
This paper proposed a fingerprint compression based on sparse representation. The proposed method has the ability by updating the dictionary. The specific process is as follows: construct a base matrix whose columns represent features of the fingerprint images, referring the matrix dictionary whose columns are called atoms; for a given whole fingerprint, divide it into […]