• Journal of Computing Science and Engineering
• /
• 제11권1호
• /
• pp.1-8
• /
• 2017

Naive Bayes nearest neighbor (NBNN) is a simple image classifier based on identifying nearest neighbors. NBNN uses original image descriptors (e.g., SIFTs) without vector quantization for preserving the discriminative power of descriptors and has a powerful generalization characteristic. However, it has a distinct disadvantage. Its memory requirement can be prohibitively high while processing a large amount of data. To deal with this problem, we apply a spherical hashing binary code embedding technique, to compactly encode data without significantly losing classification accuracy. We also propose using an inverted index to identify nearest neighbors among binarized image descriptors. To demonstrate the benefits of our method, we apply our method to two existing NBNN techniques with an image dataset. By using 64 bit length, we are able to reduce memory 16 times with higher runtime performance and no significant loss of classification accuracy. This result is achieved by our compact encoding scheme for image descriptors without losing much information from original image descriptors.

• Journal of Computing Science and Engineering
• /
• 제9권4호
• /
• pp.204-213
• /
• 2015

Under the conditional independence assumption among local features, the Naive Bayes Nearest Neighbor (NBNN) classifier has been recently proposed and performs classification without any training or quantization phases. While the original NBNN shows high classification accuracy without adopting an explicit training phase, the conditional independence among local features is against the compositionality of objects indicating that different, but related parts of an object appear together. As a result, the assumption of the conditional independence weakens the accuracy of classification techniques based on NBNN. In this work, we look into this issue, and propose a novel Bayesian network for an NBNN based classification to consider the conditional dependence among features. To achieve our goal, we extract a high-level feature and its corresponding, multiple low-level features for each image patch. We then represent them based on a simple, two-level layered Bayesian network, and design its classification function considering our Bayesian network. To achieve low memory requirement and fast query-time performance, we further optimize our representation and classification function, named relation-based Bayesian network, by considering and representing the relationship between a high-level feature and its low-level features into a compact relation vector, whose dimensionality is the same as the number of low-level features, e.g., four elements in our tests. We have demonstrated the benefits of our method over the original NBNN and its recent improvement, and local NBNN in two different benchmarks. Our method shows improved accuracy, up to 27% against the tested methods. This high accuracy is mainly due to consideration of the conditional dependences between high-level and its corresponding low-level features.