The neocognitron is a neural model which can recognize a pattern even when it is shifted in position, changed in size, or distorted. However, the complexity of its structure and its algorithm makes it difficult to tun...
详细信息
The neocognitron is a neural model which can recognize a pattern even when it is shifted in position, changed in size, or distorted. However, the complexity of its structure and its algorithm makes it difficult to tune its parameters and to specify the detail of its structure. The characteristics of this model are measured as the relationship between the degree of distortion of the input and the tolerance of the model. Computational experiments show that the pyramid has a suitable structure for implementing a neocognitron, provided that the input has a relatively low spatial frequency.< >
Many objects that appears in digital images are bounded by straight lines. Curves are often detected as series of edges. The detection of the straightness of those edge sequences is a major problem in image interpreta...
详细信息
Many objects that appears in digital images are bounded by straight lines. Curves are often detected as series of edges. The detection of the straightness of those edge sequences is a major problem in image interpretation. In this paper the RULI chain code is used for encoding geometric configurations. Rosenfeld ( IEEE Trans. Comput. C-23 , 1974, 1264–1269) and Ronse ( Pattern Recognit. Lett. 3 , 1985, 323–326) used the “chord property” to identify straight lines. While this test takes O(n ∗ ∗ 2) steps, the algorithm discussed in this paper only takes O ( n ) steps, where n is the number of code elements. Furthermore, the algorithm calculates the interval that delimits the slope of the straight line.
暂无评论