Zero-shot learning (ZSL) aims to classify images of unseen classes by learning relationship between visual and semantic features. Existing works have been improving recognition accuracy from various approaches, but they employ computationally intensive algorithms that require iterative optimization. In this work, we revisit the primary approach of the pattern recognition, ı.e., nearest neighbor classifiers, to solve the ZSL task by an extremely simple and fast way, called SimpleZSL. Our algorithm consists of the following three simple techniques: (1) just averaging feature vectors to obtain visual prototypes of seen classes, (2) calculating a pseudo-inverse matrix via singular value decomposition to generate visual features of unseen classes, and (3) inferring unseen classes by a nearest neighbor classifier in which cosine similarity is used to measure distance between feature vectors. Through the experiments on common datasets, the proposed method achieves good recognition accuracy with drastically small computational costs. The execution time of the proposed method on a single CPU is more than 100 times faster than those of the GPU implementations of the existing methods with comparable accuracies.

Nearest-neighbor-search classifiers are attractive but they have high intrinsic computational demands which limit their practical application. In this paper, we propose a coprocessor for k (k with k≥1) nearest neighbor (kNN) classification in which squared Euclidean distances (SEDs) are mapped into the clock domain for realizing high search speed and energy efficiency. The minimal SED searching is carried out by weighted frequency dividers that drastically reduce the normally exponential increase of the worst-case search-clock number with the bit width of vector components to only a linear increase. This also results in low power dissipation and high area-efficiency in comparison to the traditional method using large numbers of adders and comparators. The kNN classifier determines the class of an unknown input sample with a majority decision among the k nearest reference samples. The required majority-decision circuit is integrated with the clock-mapping-based minimal-SED searching architecture and proceeds with the classification immediately after identification of each of the k nearest references. A test chip in 180 nm CMOS technology, which can process 8 dimensions of 32 reference vectors in parallel, achieves low power dissipation of 40.32 mW (at 51.21 MHz clock frequency and 1.8 V supply voltage). Significantly, the distance search circuit consumes only 5.99 mW. Feature vectors with different dimensionality up to 2048 dimensions can be handled by the designed coprocessor due to a dimension extension circuit, enabling large flexibility for usage in different application.

This paper presents a novel algorithm for Nearest Neighbor (NN) classifier. NN classification is a well-known method of pattern classification having the following properties: * it performs maximum-margin classification and achieves less than twice the ideal Bayesian error, * it does not require knowledge of pattern distributions, kernel functions or base classifiers, and * it can naturally be applied to multiclass classification problems. Among the drawbacks are A) inefficient memory use and B) ineffective pattern classification speed. This paper deals with the problems A and B. In most cases, NN search algorithms, such as k-d tree, are employed as a pattern search engine of the NN classifier. However, NN classification does not always require the NN search. Based on this idea, we propose a novel algorithm named k-d decision tree (KDDT). Since KDDT uses Voronoi-condensed prototypes, it consumes less memory than naive NN classifiers. We have confirmed that KDDT is much faster than NN search-based classifier through a comparative experiment (from 9 to 369 times faster than NN search based classifier). Furthermore, in order to extend applicability of the KDDT algorithm to high-dimensional NN classification, we modified it by incorporating Gabriel editing or RNG editing instead of Voronoi condensing. Through experiments using simulated and real data, we have confirmed the modified KDDT algorithms are superior to the original one.

To prevent blindness from diabetic retinopathy, periodic screening and early diagnosis are neccessary. Due to lack of expert ophthalmologists in rural area, automated early exudate (one of visible sign of diabetic retinopathy) detection could help to reduce the number of blindness in diabetic patients. Traditional automatic exudate detection methods are based on specific parameter configuration, while the machine learning approaches which seems more flexible may be computationally high cost. A comparative analysis of traditional and machine learning of exudates detection, namely, mathematical morphology, fuzzy c-means clustering, naive Bayesian classifier, Support Vector Machine and Nearest Neighbor classifier are presented. Detected exudates are validated with expert ophthalmologists' hand-drawn ground-truths. The sensitivity, specificity, precision, accuracy and time complexity of each method are also compared.

This paper proposes a novel algorithm for image feature extraction-the dual two-dimensional fuzzy class preserving projections ((2D)2FCPP). The main advantages of (2D)2FCPP over two-dimensional locality preserving projections (2DLPP) are: (1) utilizing the fuzzy assignation mechanisms to construct the weight matrix, which can improve the classification results; (2) incorporating 2DLPP and alternative 2DLPP to get a more efficient dimensionality reduction method-(2D)2LPP.

A learning algorithm is presented for nearest neighbor pattern classifiers for the cases where mixed supervised and unsupervised training data are given. The classification rule includes rejection of outlier patterns and fuzzy classification. This partially supervised learning problem is formulated as a multiobjective program which reduces to purely super-vised case when all training data are supervised or to the other extreme of fully unsupervised one when all data are unsupervised. The learning, i. e. the solution process of this program is performed with a gradient method for searching a saddle point of the Lagrange function of the program.