Jan Turan

License Plate Localization and Storage Method

Though several effective image processing algorithms are created nowadays, their application is often limited by huge computation requirements, making real time operation impossible. Two major issues can be distinguished in license plate number identification, i.e. the localization of the number plate in the picture and the recognition of characters within the identified area. Neither of the tasks mentioned is easy, requiring considerable processing time, but some measurements indicate that finding and extracting characters often takes 20-25 times longer than recognizing them. The localization method introduced in the following are intended to reduce this difference. The paper also introduces wavelet-transformation based solution for efficient storage of cars pictures.

H.264/AVC multiple reference video frames

H.264/AVC standard for video coding uses multiple reference frames to enhance the coding efficiency. The quantity of increased computation is linearly proportional to the number of reference frames. This paper proposed the motion estimation of the multi macroblocks, taking into account the low complexity and fast multiple reference selection method. The simulation results show that the speed of the proposed method is over two times faster than that of the original scheme adopted in reference software, while keeping the similar video quality and bitrate.

Image Processing with Invertible Rapid Transform

The proposed paper deals with image processing using invertible rapid transform (IRT). A software tool for image processing using IRT is presented.

Signal Processing Tool Based on Invertible Rapid Transform

The proposed paper deals with the signal processing using Invertible Rapid Transform (IRT). A software tool for signal and image processing using IRT is presented.

Architecture of Transform Based Invariant Feature Memory

Presented paper deals with the problem of design transform based invariant associative image memory. Invariant feature selection is solved using the Trace transform and the Karhunen -Loeve transform (TT-KLT). System performance was evaluated in experiments with original images and their different modifications.

DEPLOYMENT OF CONSTRAINED DELAUNAY MESH IN VOP SHAPE CODING

The work presents an alternative method for encoding shape-information of video objects, which is a new requirement in the recent revolution of video codec scheme: compressing and transmitting object-based video streams. The proposed method takes the advantage of the latest development in the video encoding – motion compensation on the base of mesh presentation of frame – to complete its target. The so-called constrained Delaunay mesh is deployed to represent video objects, which are detected from a previous video object detector (in a consistent case of scene, detector can simply function like a segmenting phase of video frame). This special mesh structure in one hand constructs the base for successive motion compensation taking root on mesh-vertices. In another hand, the virtue of constrained property opens a possibility to encode the shape of video object implicitly, therefore it reduces the amount of transmitted information. With constrained Delaunay mesh, shape information of objects is presented with polygon, therefore lossy. The problem can be alleviated by increasing the number of boundary vertices at the cost of bandwidth. The work also puts a stress on controlling this trade-off. Results of integrating the proposed method into a full VOP codec scheme are encouraging.