This study is emphasized on different types of normalization. Each of which was tested against the ID3 methodology using the HSV data set. Number of leaf nodes, accuracy and tree growing time are three factors that were taken into account. Comparisons between different learning methods were accomplished as they were applied to each normalization method. A new matrix was designed to check for the best normalization method based on the factors and their priorities. Recommendations were concluded.

No abstract

No abstract

Invisible watermarking methods have been applied in frequency domains, trying to embed a small image inside a large original image. The original bitmap image will be converted into frequency domain to obtain the discrete cosine transform (DCT) matrices from its blocks. The bits of the logo image are embedded in random color components of the original image, as well as in random positions in each selected block. These positions are alternating current (AC) coefficients of the DCT matrix. The randomness is obtained from RC4 pseudorandom bit generator that determines in which color component this logo image bits will be embedded. The embedded bits have been hidden in random blocks in the image, which are chosen according to a (semi-random) function proposed in this work.