Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Jouni Paakkonen"'
Publikováno v:
Machine Vision and Applications. 26:103-113
The aim of this paper is to introduce an image source-independent automated method for segmentation and classification of prostate glands. This research focuses on light microscopic images of the samples from different laboratories using the same sta
Publikováno v:
2009 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).
The aim of this paper is to apply approximated path distance transform on curved space (APDTOCS) to color images of human tissue samples. Standard DTOCS was used as a reference method. APDTOCS reveals more detail than standard DTOCS especially in par
Publikováno v:
SITIS
The aim of this project is to find suitable, reliable and fast methods for computational cancer histopathology. Clustering of FTIR spectra has been done before, but this paper uses features instead of whole spectra or its second derivative. The resol
Publikováno v:
2009 IEEE 5th International Conference on Intelligent Computer Communication and Processing.
The aim of this paper is to apply distance transform on curved space (DTOCS) to grayscale images of human tissue samples. Also a new approximated path DTOCS (APDTOCS), which approximates distances on curved space using only the end points of the path
Publikováno v:
2008 9th International Conference on Signal Processing.
The aim of this paper is to test which multiresolution level should be used in lossy wavelet compression. The measurements were done using two sizes of test images, three wavelet base functions and three color spaces. Different orders of each wavelet