|
CVGResearch
Home |
Recognition Objects tend to fall into categories. Those of the same class usually share common features while those of different classes possess distinctive features, which makes recognition possible. A key (futuristic) goal of computer vision is to empower the machine with the superb recognition ability of the human vision system. Object recognition has found many successful applications such as character, fingerprint, face recognition, and also plays a key role in many fields such as video surveillance and remote sensing, product inspection, biological research and medical diagnosis. |
|||||
|
Rectified nearest feature line segment for pattern classification.
|
||||||
| Abstract. This paper points out and analyzes the advantages and drawbacks of the nearest feature line (NFL) classifier. To overcome the shortcomings, a new feature subspace with two simple and effective improvements is built to represent each class. The proposed method, termed rectified nearest feature line segment (RNFLS), is shown to possess a novel property of concentration as a result of the added line segments (features), which significantly enhances the classification ability. Another remarkable merit is that RNFLS is applicable to complex tasks such as the two-spiral distribution, which the original NFL cannot deal with properly. Finally, experimental comparisons with NFL, NN(nearest neighbor), k-NN and NNL (nearest neighbor line) using both artificial and real-world data-sets demonstrate that RNFLS offers the best performance. |
 |
|||||
|
Improving nearest neighbor classification with cam weighted distance.
Chang Yin Zhou, Yan Qiu Chen. Pattern Recognition, Volume 39, Issue 4, Pages 635-645, 2006 |
||||||
| Abstract. Nearest neighbor (NN) classification assumes locally constant class conditional probabilities, and suffers from bias in high dimensions with a small sample set. In this paper, we propose a novel cam weighted distance to ameliorate the curse of dimensionality. Different from the existing neighborhood-based methods which only analyze a small space emanating from the query sample, the proposed nearest neighbor classification using the cam weighted distance (CamNN) optimizes the distance measure based on the analysis of inter-prototype relationship. Our motivation comes from the observation that the prototypes are not isolated. Prototypes with different surroundings should have different effects in the classification. The proposed cam weighted distance is orientation and scale adaptive to take advantage of the relevant information of inter-prototype relationship, so that a better classification performance can be achieved. Experiments show that CamNN significantly outperforms one nearest neighbor classification (1-NN) and k-nearest neighbor classification (k-NN) in most benchmarks, while its computational complexity is comparable with that of 1-NN classification. |
 |
|||||
|
On Neural-Network Implementations of k-Nearest Neighbor Pattern Classifiers.
Yan Qiu Chen, Robert I. Damper, Mark S. Nixon. IEEE Trans. Circuits and Systems- I: Fundamental Theory and Applications, Vol. 44, No. 7, 1997 |
||||||
| Abstract. The k-nearest neighbor (k-NN) decision rule is the basis of a well-established, high-performance pattern-recognition technique but its sequential implementation is inherently slow. More recently, feedforward neural networks trained on error backpropagation have been widely used to solve a variety of pattern-recognition problems. However, it is arguably unnecessary to learn such a computationally intensive solution when one (i.e., the k-NN rule) is effectively available a priori, especially given the well-known pitfalls of backpropagation. Accordingly, there is some interest in the literature in network implementations of this rule, so as to combine its known, good performance with the speed of a massively parallel realization. In this paper, we present a novel neural-network architecture which implements the k-NN rule and whose distinctive feature relative to earlier work is its synchronous (i.e., clocked) nature. Essentially, it has a layered, feedforward structure but, in its basic form, also incorporates feedback to control sequential selection of the k neighbors. The principal advantages of this new scheme are the avoidance of the stability problems which can arise with alternative asynchronous feedback (lateral-inhibition) circuits, the restriction of analog weights to the first hidden layer and the fact that network design uses noniterative weight calculations rather than iterative backpropagation. Analysis of the network shows that it will converge to the desired solution (faithfully classifying the input pattern according to the k-NN rule) within (2k-1) clock cycles. Apart from minor changes which can be effected externally, the same design serves for any value of k. The space complexity of the “brute-force” network implementation is O(N^2) units, where N is the number of training patterns, and it has O(dN^2) analog weights where d is the dimensionality of these patterns. Thus, some modifications to reduce the required number of units (and, thereby, weighted connections) are considered. Overall, this paper affords for high-speed, parallel implementations of proven pattern-classification techniques. | ||||||
|
Generating-shrinking algorithm for learning arbitrary classification.
Yan Qiu Chen, David W. Thomas, Mark S. Nixon. Neural Networks, Volume 7, Issue 9, Pages 1477-1489, 1994 |
||||||
| Abstract. This paper proposes a novel generating-shrinking algorithm that builds and then shrinks a three-layer feedforward neural network to achieve arbitrary classification in n-dimensional Euclidean space. The algorithm offers guaranteed convergence to a 100% correct classification rate on training patterns. Decision regions resulting from the algorithm are analytically described, so the generalisation behaviour of the trained network is analytically known. By altering the value of a reference number, the trained neural classifier can achieve scale-invariant generalisation as well as equal-distance generalisation to accommodate different requirements. | ||||||
|
|
||||||