Timo Jääskeläinen

Learn More
—The information content of remotely sensed data depends primarily on the spatial and spectral properties of the imaging device. This paper focuses on the classification performance of the different spectral features (hyper-and multispectral measurements) with respect to three tree species. The Support Vector Machine was chosen as the classification(More)
We present a new cooccurrence matrix based approach for multispectral texture analysis. The spectral and spatial domains of the multispectral textures are processed separately. The color space used in this study is represented by subspaces and it is class$ed by the averaged learning sub-space method (ALSM). In the spatial domain we use a generalized(More)
Multi-spectral images are becoming more common in industrial inspection tasks where the colour is used as a quality measure. In this paper we propose a spectral cooccurrence matrix-based method to analyse multi-spectral texture images, in which every pixel contains a measured colour spectrum. We first quantise the spectral domain of the multi-spectral(More)
In this paper, we propose a simultaneous measurement system of spectral reflectance and shape of an object with the use of color gray code structured patterns and an imaging spectrograph. Color and shape information are very important for us to recognize objects. Therefore, we have proposed an earlier system which is able to measure spectral reflec-tance(More)