A Local Feature Descriptor Based on SIFT for 3D Pollen Image Recognition

Abstract

Biological particle automatic classification is an important issue in index tasking for people with pollen hypersensitivity. This paper attempts to present a local feature extraction method based on SIFT for automatic 3D pollen image recognition. In order to solve major issues in previous studies, high rate of redundant information, high feature dimensions and low recognition rate should be taken into account. Therefore, this work focuses on a four-part novel approach, including constructing 3D Gaussian pyramid to obtain muti-scale pollen images, computing the local differential vector to explore local key points, filtering the key points by inter-layer contrast, and extracting the statistical histogram descriptor of the key points as discriminant feature for automatic classification of 3D pollen images. Experiments are performed on three standard pollen image datasets including Confocal, Pollenmonitor and CHMontior. It is concluded that the descriptor can effectively describe the pollen image and is robust to the rotation, translation and scaling of the image. INDEX TERMS Scale invariant feature transform, local feature, pollen recognition, 3D image. I. INTRODUCTION

Automatic 3D Pollen Recognition Based on Convolutional Neural Network

“…e experimental results are compared to SKLP [18] descriptors, LDP descriptors [14], faster CNN [33], and multi-CNNs [7] to verify the validity of the proposed algorithm on Confocal-E dataset. It can be seen from the three-dimensional pollen images that different textures cover the external wall of various pollen grains, such as thorn, tumor, rod, cave, and net, which are more obvious than those in the twodimensional pollen images.…”

“…SLKP is a lightweight statistical feature extraction method based on SIFT and histogram algorithms, which can reduce the high dimensionality of the descriptors for 3D pollen images and effectively indicate the spatial relationship among 3D pixels. It is proved by [18] that SLKP provides a solution for the extension of SIFT from two dimensions to three dimensions, which can solve the problem of information loss mentioned above. e main steps of SKLP are as follows:…”

“…According to these disadvantages of pollen recognition methods mentioned above, we propose an efficient and robust algorithm to identify different categories of pollen grains. Firstly, we detect local stable regions of pollen images from spatial local key point (SKLP) [18] descriptor as the input of the next stage.…”

Pattern recognition methodologies for pollen grain image classification: a survey

“…A different approach is done by the authors of [65]. Instead of relying on descriptors for specific features the authors utilize the SIFT method [40] on 3D pollen images.…”

“…This produces a vector histogram descriptor, describing the statistical distribution of the gradient vectors for the key points. The experiments were performed on three different data sets: Confocal [54], Pollenmonitor [46], and CHMonitor [65] (taking 25% random images per category as training images) achieving an average precision of 88.25% (over all data sets).…”