Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: homomorphic filtering

Sortuj według:

Ogranicz wyniki do:

Image Preprocessing for Illumination Invariant Face Verification

Leszczyński M.

Journal of Telecommunications and Information Technology

2010

nr 4

19-25

Performance of the face verification system depend on many conditions. One of the most problematic is varying illumination condition. In this paper 14 normalization algorithms based on histogram normalization, illumination properties and the human perception theory were compared using 3 verification methods. The results obtained from the experiments showed that the illumination preprocessing methods significantly improves the verification rate and it's a very important step in face verification system.

Segmentation based on homomorphic filtering and improved seeded region growing for mobile robots tracking in image sequences

Kasinski A. J., Hamdy A. M.

Machine Graphics and Vision

2001

Vol. 10, No. 4

447-466

In this paper, we present a method for extracting of mobile robots in a sequence of noisy frames, assuming a complex background composed of textured floor, illuminated unvenly. A homomorphic filter if used, as a preprocessor, to enhance the acquired frames by eliminating the illumination component and emphasizing the reflectance component of the image function. To speed up preprocessing of each frame, filtering is only applied to the pixels belonging to the regions of interest (ROI). In all the tested cases, homomorphic--filtering led to better results than those obtained without preprocessing. The segmentation process has been based on seeded region growing procedure for reconstructing the shape of the mobil robot. We proposed automatic seed points selection in the binarized difference image, and use an adaptive threshold. This use eliminates or at least considerably reduces false negative detections, and reduces sensitivity of aggregation results to the selected seed points as compared to the classical seeded region growing procedure. Additionally, by imposing a condition of strong connectivityu bettween a seed point and its neighborhood, aggregation of undesired pixels efficiently eliminates false positive detections. Implementation of segmentation and tracking can be run in real time. High tracking accuracy has been obtained through out all the frames in a test sequence.