Desktop version

Home arrow Engineering arrow Cellular Image Classification

Introduction

As we mentioned in Chap.4, all the improved coding methods represent images more accurately and achieve impressive image classification performance. However, information loss in feature quantization is still inevitable and affects the performance for good image classification performance. To avoid information loss caused by coding, Naive Bayes Nearest Neighbor (NBNN) method [1] is proposed by retaining all of the feature descriptors. It shows competitive classification performance with coding based methods as it alleviates information loss and keeps the discrimination of input features. However, the NBNN is sensitive to noisy features and easy to be dominated by outlier features. To simultaneously inherit the advantage of the BoW framework and the NBNN method, LDC method [2] has been proposed recently to utilize the discriminative information lost due to the traditional coding schemes. It transforms each local feature to a distance vector via calculating neighbors in every class-specific manifold.

In this chapter, we propose a novel LLDC method to increase the accuracy of staining pattern classification. The LLDC method adopts the feature extraction-codingpooling framework based on local distance vector which is a modification of the

© Springer International Publishing AG 2017 X. Xu et al., Cellular Image Classification, DOI 10.1007/978-3-319-47629-2_5

distance vector. Local distance vector is generated by using only the local neighbors in a merged feature dataset instead of calculating neighbors in every class-specific feature dataset. Therefore it can ignore disturbance from isolated classes. Using image-to-class distance makes it more class-specific as desired for classification. Meanwhile, distance vector in LDC method is obtained by using a linear coding scheme which aggravates the information loss. Local distance vector is only based on Euclidean distance and avoids coding process in distance vector transformation, therefore it is more discriminative. Furthermore, using the robust image-to-class distance relieves the strict requirement of the following pooling procedure on image spatial layout. In addition, it is proved that image representations via coding distance patterns are complementary to the ones obtained by the conventional coding schemes [2]. Therefore, we directly concatenate the image representations based on local distance vector and local features to achieve superior performance.

In summary, the main contributions of this study are as threefold: (i) We propose a novel local distance vector based on the image-to-class distance. It is more class- specific than original local feature. Unlike distance vector, it eliminates the need to calculate the distance for each class therefore it can speed up the calculation and achieve better classification performance by ignoring the disturbance from the distant classes. (ii) We propose a LLDC method based on the transformed local distance vector. It takes the advantages of the BoW framework and the NBNN method. It reduces the information loss caused by traditional coding methods while capturing salient features. (iii) The combination of image representations produced by the LLDC method and the ones produced by the traditional coding methods, can yield superior performance compared with only using single representation. Experiments on two public HEp-2 cells datasets consistently show that the image representation produced by the LLDC framework achieves better performance compared with state- of-the-arts coding methods.

 
Source
< Prev   CONTENTS   Source   Next >