We present a method for automatic textual annotation of compressed video. Initially, cuts are detected in the video sequence where consecutive frames show a large difference. Key frames are then extracted to represent each shot. A video sequence is, thus, condensed into a few images, hence this forms a compact key frame representation of the video. Each key frame is compared with an annotated d...

The detection of defective parts in a factory is usually performed by the human eye. Therefore, heavy manpower is in demand for minor enterprises. An image processing system is desired to solve this drawback. However, due to the variety of the products characteristics, an general algorithm is needed that can adapt to these characteristics. Therefore, in this paper, the key pad parts’ characteri...

Video fingerprints can help us identify a large amount of video on the Internet and enable interesting services to the end user. One of the main challenges for video fingerprints is for them to be robust against intentional/unintentional geometric modifications on the content such as scaling, aspect ratio conversion, rotation and cropping. In this paper, we review a number of fingerprinting met...

This paper aims to find the minimum sample size of the camera reference image set that is needed to build a sensor fingerprint of a high performance. Today’s methods for building sensor fingerprints do rely on having a sufficient number of camera reference images. But, there is no clear answer to the question of how many camera reference images are really needed? In this paper, we will analyze ...

Visual Secret Sharing (VSS) is a powerful approach for protecting image sharing through unsecured computer network such as the Internet. Pixel expansion and bad image quality are the most common problems of this approach. Visual secret sharing technique is proposed for grayscale images to eliminate pixel expansion problem using image compression. The experimental results and security analysis i...

We present a class of image fusion techniques to automatically combine images of a scene captured under different illumination. Beyond providing digital tools for artists for creating surrealist images and videos, the methods can also be used for practical applications. For example, the non-realistic appearance can be used to enhance the context of nighttime traffic videos so that they are easi...

Fingerprint images frequently have poor characteristics, because these traces are captured in crime places and are left on objects of different structure. For this reason, a lot of fingerprints have to be rejected they are useless in identification processes. Fortunately, in some cases, low quality fingerprints can be additionally analysed by means of special algorithms. In this paper, a new fi...

A novel watermarking technique is proposed to embed a semi-watermark in digital images. Before embedding the watermark, a M-dimensional vector is extracted from the original data. Watermarking is achieved by modifying this vector to another particular vector according to the private keys and the watermark. A dual-key system is used to reduce the chance for the removal of watermark. The watermar...

Video databases can be searched for visual content by searching over automatically extracted key frames rather than the complete video sequence. Many video materials used in the humanities and social sciences contain a preponderance of shots of people. In this paper, we describe our work in semantic image retrieval of person-rich scenes (key frames) for video databases and libraries. We use an ...

In this paper, we propose a method to embed the color information of an image in a corresponding grey-level image. The objective of this work is to allow free access to the grey-level image and give color image access only if you own a secret key. This method is made of three major steps which are the color quantization, the ordering and the data hiding. The originality of this paper is to buil...