Online Sorting of the Film on Cotton Based on Deep Learning and Hyperspectral Imaging

Abstract

Mulch film is usually mixed in with cotton during machine-harvesting and processing, which reduces the cotton quality. This paper presents a novel sorting algorithm for the online detection of film on cotton using hyperspectral imaging with a spectral region of 1000-2500 nm. The sorting algorithm consists of a group of stacked autoencoders, two optimization modules and an extreme learning machine (ELM) classifier. The variable-weighted stacked autoencoders (VW-SAE) are constructed to extract the features from hyperspectral images, and an artificial neural network (ANN), which is one optimization module, is applied to optimize the parameters of the VW-SAE. Then, the extracted features are input in the ELM to classify four types of objects: background, film on background, cotton and film on cotton. The ELM is optimized by a new optimizer (grey wolf optimizer), which can adjust the hidden nodes and parameters of the ELM simultaneously. A group of experiments was carried out to evaluate the performance of the proposed sorting algorithm using cotton that was provided by a Xinjiang municipality cotton ginning company. The experimental results show that the VW-SAE can improve the classification accuracies by approximately 15 %. The overall recognition rate of the proposed algorithm is over 95 %, and its recognition time is comparable to some state-of-the-art methods. INDEX TERMS Cotton, sorting system, plastic film, deep learning, hyperspectral imaging, grey wolf optimizer, variable-wise weighted stacked autoencoder.

Recognition and Grasping of Disorderly Stacked Wood Planks Using a Local Image Patch and Point Pair Feature Method

“…Traditional autoencoders [32][33][34] are generally fully connected, which will generate a large number of redundant parameters. The extracted features are global, local features are ignored, and local features are more important for wood texture recognition.…”

Advances in Optimisation Algorithms and Techniques for Deep Learning

“…The GWO is a SI optimiser that has recently been applied to DL research where the GWO was used to optimise the number of hidden layers and weights of the neural network [56]. It is proposed by [57], and it mimics the grey wolves internal leadership hierarchy in-which four key categories of wolves including alpha, beta, omega and delta was used to represent the best individual as alpha, the second-best individual as beta, the third-best individual is recorded as delta, and the remaining individuals are considered as omega.…”

“…The vectors A and C is obtained by (42) where r 1 and r 2 are random vectors located in the slope of [0, 1] and the value of a lies between 0and2. The GWO has been recently applied in optimising flight models, especially to identify the flight state using CNNs [58] as well as modifying the hidden parameters of the SAE architecture [56]. Researchers suggest that the GWO is simple in design, fast with very high search precision, thereby making it easy to realise and implement in practical engineering applications [54].…”

“…Researchers suggest that the GWO is simple in design, fast with very high search precision, thereby making it easy to realise and implement in practical engineering applications [54]. The GWO was applied to the stacked auto-encoder (SAE) architecture for sorting different kinds of cotton [56] as well as for classifying extracted features of diabetic retinopathy dataset [59]. The GWO exploration has provided numerous improved versions, with the first being the improved Grey Wolf Optimiser (IGWO), proposed [54], as well as the multi-objective criteria version named multi-objective grey wolf optimizer (MOGWO) for DL application.…”

Detecting Defects on Solid Wood Panels Based on an Improved SSD Algorithm

“…With the development of these technologies, wood inspection has gradually made the transition to automated inspection and classification. Due to the ongoing improvement in image acquisition equipment and the expanding role of deep learning technology in the field of image recognition, research has focused on combining machine vision technology with deep learning networks [ 17 ] and applying them to the non-destructive inspection of wood surfaces. For example, He et al [ 18 ] used a linear array CCD camera to obtain wood surface images, and proposed a hybrid total convolution neural network (Mix-FCN) for the recognition and location of wood defects; however, the network depth was too deep and required too much calculation.…”