Fruit Image Recognition Based on Census Transform and Deep Belief Network_Qi Xin_ICMTEL 2020.pdf

Hubble

9页

0次

2023-01-30

免费下载

Fruit Image Recognition Based on Census

Transform and Deep Belief Network

Qi Xin

, Shaohai Hu

1(&)

, Shuaiqi Liu

2,3(&)

, Hui Lv

Shuai Cong

5(&)

, and Qiancheng Wang

College of Computer and Information,

Beijing Jiaotong University, Beijing 100044, China

shhu@bjtu.edu.cn

College of Electronic and Information Engineering, Hebei University,

Baoding 071000, China

shdkj-1918@163.com

Machine Vision Technology Creation Center of Hebei Province,

Baoding 071000, China

Beagledata Technology (Beijing) Co., Ltd., Beijing 100089, China

Industrial and Commercial College, Hebei University,

Baoding 071000, Hebei, China

congshuai@hbu.edu.cn

Abstract. Fruit image recognition plays an important role in the ﬁelds of smart

agriculture and digital medical treatment. In order to overcome the disadvantage

of the deep belief networks (DBN) that ignores the local structure of the image

and is difﬁcult to learn the local features of the image, and considering that the

fruit image is affected by the change of illumination, we propose a new fruit

image recognition algorithm based on Census transform and DBN. Firstly, the

texture features of fruit images are extracted by Census transform. Secondly,

DBN is trained by Census features of fruit images. Finally, DBN is used for fruit

image recognition. The experimental results show that the proposed algorithm

has a strong feature learning ability, and the recognition performance is better

than the traditional recognition algorithm.

Keywords: Fruit image recognition

 Deep belief network  Census transform

1 Introduction

Nowadays, the sharp increase in the amount of image data makes the number of images

in general image recognition tasks become larger and larger, which also makes it

difﬁcult for traditional methods to meet people’ s needs. As a new subject in machine

learning, deep learning has a lot of achievements in various ﬁelds. Compared with the

artiﬁcial feature extraction method, the data features acquired through deep learning

model are more representative of the rich inner information of big data and good

features can be learned automatically without manual feature extraction. Therefore,

deep learning is the future and will receive more attention in big data analytics [1–3].

Y.-D. Zhang et al. (Eds.): ICMTEL 2020, LNICST 327, pp. 438–446, 2020.

https://doi.org/10.1007/978-3-030-51103-6_39

Fruit image recognition plays an important role in the ﬁelds of smart agriculture and

digital medical [ 4 , 5]. With the rapid development of smart agriculture and digital

medical in recent years, fruit image recognition has attracted more and more

researchers’ attention. In order to meet the needs of large-scale a nd efﬁcient fruit

recognition and classiﬁcation, researchers began to identify fruit image with different

algorithms. For example, in [6], the authors proposed a fruit classiﬁcation based on six

layer convolutional neural network and the classiﬁcation accuracy is higher than that of

traditional single feature. In [7], the authors present an automatic fruit recognition

system for classifying and identifying fruit types and which is capable of automatically

recognize the fruit name with a high degree of accuracy. And in [8], the authors

proposed Kiwifruit recognition method at night based on fruit calyx image, whose

recognition rate reached 94.3%. And in [9], the authors propos ed a fast and accurate

object recognition method especially for fruit recognition to be used for mobile

environment. They combined color, shape, texture and intensity into their associated

code ﬁelds to generate an object code that could be used as a search key for the feature

database. And in [10], the authors given a fruit recognition method via image con-

version optimized through evolution strategy principal component analysis and

achieved a better recognition effect through the pretreatment, training and recognition

of fruit images, with an average recognition rate of over 92%.

In general, the process of fruit image recognition system mainly focuses on pre-

treatment and feature extraction. In this kind of recognition system, fruit image

acquisition is mostly conducted by placing the collected fruit in a strictly deﬁned

background in order to ensure that the recognition system is less interfered by the

outside world, so as to improve the recognition accuracy of the system. However, the

image in the actual environment is easily affected by the factors such as illumination

change, fruit reﬂection and shielding, which in vary degrees impact the recognition

accuracy of fruit image. In fruit recognition system, fruit features mainly include odor,

color, shape and texture. While in the process of growth, different environment will

lead to difference in shapes, sizes and colors. In addition, natural light intensity and

shadow will also be different when frui t images are collected, which will affect the

accuracy of image recognition. What’s more, the complexity of the color and texture

features of fruit images also makes the recognition more difﬁcult. Therefore, better

recognition algorithms are needed to solve this problem.

As a representative method in the deep learning, DBN is quite different from the

previous algorithms in terms of training method structure. By adopting the idea of

layered training, the training speed of DBN is greatly improved [11, 12]. In addition,

the idea of layering also increases the system’s ability to express complex functions.

DBN usually takes pixel-level images as input and extracts the abstract features of the

input images from bottom to top, from simple to complex, which is a process of

automatic mining useful information in the data. However, general pixel-level images

are easily affected by illumination and other factors, which affects the extraction of

essential features of input samples in DBN. In order to improve the fruit image

recognition performance of DBN under different illumination, we propose a new

method combining Census transform with DBN to extract the texture features of

images through Census transform to eliminate the inﬂuence of ununiform lighting on

the recognition results.

Fruit Image Recognition 439