AI-enabled robotic sorting for circular textile waste management: A scalable solution for India’s recycling sector

Oral cancer is a complex wide spread cancer, which has high severity. Using advanced technology and deep learning algorithm early detection and classification are made possible. Medical imaging technique, computer-aided diagnosis and detection can make potential changes in cancer treatment. In this research work, we have developed a deep learning algorithm for automated, computer-aided oral cancer detecting system by investigating patient hyperspectral images. To validate the proposed regression-based partitioned deep learning algorithm, we compare the performance with other techniques by its classification accuracy, specificity, and sensitivity. For the accurate medical image classification objective, we demonstrate a new structure of partitioned deep Convolution Neural Network (CNN) with two partitioned layers for labeling and classify by labeling region of interest in multidimensional hyperspectral image. The performance of the partitioned deep CNN was verified by classification accuracy. We have obtained classification accuracy of 91.4% with sensitivity 0.94 and a specificity of 0.91 for 100 image data sets training for task classification of cancerous tumor with benign and for task classification of cancerous tumor with normal tissue accuracy of 94.5% for 500 training patterns was obtained. We compared the obtained results from another traditional medical image classification algorithm. From the obtained result, we identify that the quality of diagnosis is increased by proposed regression-based partitioned CNN learning algorithm for a complex medical image of oral cancer diagnosis.

It is significant to identify the moldy status of stored maize by fungi infection in the early stage. Hyperspectral imaging (HSI) combined with the sparse auto-encoders (SAE) and convolutional neural network (CNN) algorithms was used to classify the moldy grades of maize kernels. The HSI data were obtained in the range of 400–1000 nm, and four grades from health to heavy mildew were distinguished using the measured fungal spores of maize. The depth spectral features were represented using SAE and the image features were extracted by CNN. K nearest neighbors, support vector machine (SVM), and partial least squares discriminant analysis classifiers were combined with the spectral and image features to establish classification models to identify the different moldy grades of maize kernels. The comparison results indicated that the fusion of SAE and CNN combined with the SVM classifier to construct the SAE-CNN-SVM model had the most satisfactory identification result with high correct recognition rates of 99.47% and 98.94% for the training and testing sets, respectively, and the values of sensitivity and specificity were 0.95–1. The moldy grades were presented intuitively on the maize image based on pixels or kernel-wise. Therefore, the HSI with the SAE-CNN-SVM model had good recognition ability for the early detection of moldy maize kernels, which could potentially provide technical support for the development of online detection of moldy maize kernels during storage.

The purpose of this study is to develop hyperspectral imaging (HSI) for automatic detection of head and neck cancer cells on histologic slides. A compact hyperspectral microscopic system is developed in this study. Histologic slides from 15 patients with squamous cell carcinoma (SCC) of the larynx and hypopharynx are imaged with the system. The proposed nuclei segmentation method based on principle component analysis (PCA) can extract most nuclei in the hyperspectral image without extracting other sub-cellular components. Both spectra-based support vector machine (SVM) and patch-based convolutional neural network (CNN) are used for nuclei classification. CNNs were trained with both hyperspectral images and pseudo RGB images of extracted nuclei, in order to evaluate the usefulness of extra information provided by hyperspectral imaging. The average accuracy of spectra-based SVM classification is 68%. The average AUC and average accuracy of the HSI patch-based CNN classification is 0.94 and 82.4%, respectively. The hyperspectral microscopic imaging and classification methods provide an automatic tool to aid pathologists in detecting SCC on histologic slides.

Cotton is a significant economic crop. It is vulnerable to aphids (Aphis gossypii Glovers) during the growth period. Rapid and early detection has become an important means to deal with aphids in cotton. In this study, the visible/near-infrared (Vis/NIR) hyperspectral imaging system (376–1044 nm) and machine learning methods were used to identify aphid infection in cotton leaves. Both tall and short cotton plants (Lumianyan 24) were inoculated with aphids, and the corresponding plants without aphids were used as control. The hyperspectral images (HSIs) were acquired five times at an interval of 5 days. The healthy and infected leaves were used to establish the datasets, with each leaf as a sample. The spectra and RGB images of each cotton leaf were extracted from the hyperspectral images for one-dimensional (1D) and two-dimensional (2D) analysis. The hyperspectral images of each leaf were used for three-dimensional (3D) analysis. Convolutional Neural Networks (CNNs) were used for identification and compared with conventional machine learning methods. For the extracted spectra, 1D CNN had a fine classification performance, and the classification accuracy could reach 98%. For RGB images, 2D CNN had a better classification performance. For HSIs, 3D CNN performed moderately and performed better than 2D CNN. On the whole, CNN performed relatively better than conventional machine learning methods. In the process of 1D, 2D, and 3D CNN visualization, the important wavelength ranges were analyzed in 1D and 3D CNN visualization, and the importance of wavelength ranges and spatial regions were analyzed in 2D and 3D CNN visualization. The overall results in this study illustrated the feasibility of using hyperspectral imaging combined with multi-dimensional CNN to detect aphid infection in cotton leaves, providing a new alternative for pest infection detection in plants.

The textile industry is a large source of pollution due to the production of raw materials (natural and synthetic fibers), preparation and finishing processes, as well as due to textile waste, especially the post-consumer waste. This paper is an attempt to change the perception concerning such waste. In the context of circular economy, textile waste has to be conceived as a source for carbon and energy. A new attitude is compulsory due to the increase of post-consumer waste quantity since the volume of textile consumption has lately increased. Fast fashion cycle and cheaper textile products having a shorter lifetime led to an increase of the quantity of post-consumer textile waste. Demands for pollution reduction generated the concern to upcycle the textile waste in order to recover, at least partially, the materials as well as the energy consumed for their manufacture, reducing accordingly the carbon and water footprints of these products,. The scarcity of raw materials and of fossil fuels, the high environmental impact of the simple disposal of waste, imposed a new policy regarding the transformation of the linear economy which characterizes today's textile industry into a circular one, leading to a lower environmental impact. This involves the valorization of post-consumer waste by recycling or at least by a partial recovery of the materials and energy spent for the manufacture of these products. A good management of post-consumer textile waste is mandatory for attaining a zero waste target. Some good practices in the field are presented by this paper.

Hyperspectral Image (HSI) classification is one of the fundamental tasks in the field of remote sensing data analysis. CNN (Convolutional Neural Network) has been proven to be an effective deep learning model, which can extract high-level features directly from the raw data and thereby utilize rich information contained in HSI data. However, labor cost to label enough HIS data for training model is usually expensive, so that it is a strong demand of utilizing limited training data to get a satisfied classification accuracy. In this paper, we put forward a deep cube CNN model – DCNR, which is composed of a cube neighbor HSI pixels strategy, a deep CNN and a random forest classifier. In DCNR model, cubic samples, containing spectral-spatial information, are generated by putting each target pixel and its neighbors together. Then features with high representative ability, extracted by applying a specially designed cube CNN model on each cubic sample, are fed into the random forest classifier for the classification of the target pixel. Results show that DCNR model can achieve classification accuracy of 96.78%, 96.08% and 94.85% on KSC, IP and SA datasets respectively with 20% samples as training set, and 85.03%, 83.45 and 62.17% on KSC, IP and SA datasets respectively with only 1% samples as training set, significantly outperforming random forest and cube CNN models.

A correct food tray sealing is required to preserve food properties and safety for consumers. Traditional food packaging inspections are made by human operators to detect seal defects. Recent advances in the field of food inspection have been related to the use of hyperspectral imaging technology and automated vision-based inspection systems. A deep learning-based approach for food tray sealing fault detection using hyperspectral images is described. Several pixel-based image fusion methods are proposed to obtain 2D images from the 3D hyperspectral image datacube, which feeds the deep learning (DL) algorithms. Instead of considering all spectral bands in region of interest around a contaminated or faulty seal area, only relevant bands are selected using data fusion. These techniques greatly improve the computation time while maintaining a high classification ratio, showing that the fused image contains enough information for checking a food tray sealing state (faulty or normal), avoiding feeding a large image datacube to the DL algorithms. Additionally, the proposed DL algorithms do not require any prior handcraft approach, i.e., no manual tuning of the parameters in the algorithms are required since the training process adjusts the algorithm. The experimental results, validated using an industrial dataset for food trays, along with different deep learning methods, demonstrate the effectiveness of the proposed approach. In the studied dataset, an accuracy of 88.7%, 88.3%, 89.3%, and 90.1% was achieved for Deep Belief Network (DBN), Extreme Learning Machine (ELM), Stacked Auto Encoder (SAE), and Convolutional Neural Network (CNN), respectively.

Classification is a key technique in hyperspectral image (HSI) applications. Deep learning algorithms, which exhibit strong modeling and representational capabilities, have been successfully adopted in fields such as image and language processing. And convolutional neural networks (CNNs) have been used for HSI classification and some interesting results have been obtained. Owing to local connection and weight sharing, the number of parameters is reduced to some extent, but there are still many parameters and the deeper the network, the larger is the number of parameters. The network performance is strongly influenced by the parameter settings. To obtain the optimal CNN parameters for HSI classification, this paper proposes a classification method based on a CNN with parameter tuning (CNN-PT). The network parameters are tuned in turn according to the unique variable principle. Simulation results show that the proposed CNN-PT method has considerable potential for HSI classification compared to previous methods.

Performance evaluation of deep learning algorithms for heat loss damage classification in buildings from UAV-borne infrared images

Problem
 The fashion industry is the second most polluting industry globally [UNEP2021] - 85% of all textiles go to landfill each year [WEF2021]. There is growing demand for a shift to circular business models, with new concepts emerging such as “extended producer responsibility” [DEFRA2022], and policy announcements such as the EU Strategy for Sustainable and Circular Textiles, mandating Digital Product Passports (DPP) [EC2023].The Ellen McArthur Foundation [EMF2021] has stated that “Sustainability concerns among customers are also projected to heighten”. This fact, coupled with the preparation of potential new regulatory instruments such as ‘Extended Producer Responsibility’ and other critical regulatory developments, is pushing the industry to consider different and more sustainable ways of producing textile products. A new technology-infrastructure to facilitate this transition is required, to support companiesand consumers access critical data on individual garments.
 150 billion items of clothing are produced annually worldwide [EMF2022], of which around 12.5 billion were tagged in 2022, using radiofrequency identification (RFID) technology [Checkpoint2022]. The use of RFID tags is increasing rapidly, with the market projected to reach $35.6 Billion by 2030 [MarketsAndMarkets2022].
 However, there are mainly two sustainability related problems holding back the full potential of RFID in the fashion industry:
 
 
 Weaknesses in current RFID-tag technologies: low robustness, non-washability, and attachment to temporary labels not integrated with the garment itself. 12.5 Billion RFID-tags were used last year in the fashion industry, mainly for inventory management [Checkpoint2022]. Those billions of paper/metal/label tags are usually removed immediately after sale and end up in landfill (which is very bad for the environment), because they are not washable or comfortable to wear with thegarment. For garments to be traceable throughout their lifecycle (enabling efficiencies and circular models), there is a need for integrating permanent 'Digital Passports' (e.g. RFID) in each textile-based product, and for easy access to data contained in these Digital Passports.
 
 Lack of data access, exchange and integration between supply chain actors: Currently, stakeholders use their own independent data management system/s. Therefore, the biggest challenges for efficient recycling/reuse of clothing is lack of access to data on fibre/material content. This makes it very difficult to implement automated systems for breaking up and separating used clothing items into their different fibre components.
 

The use of convolutional neural networks (CNNs) to classify hyperspectral images (HSIs) is being done in contemporary research works. HSI data poses a challenge to the current technique for data analysis because of its extensive spectrum information. It has been noted that conventional CNN primarily grabs the spatial characteristics of HSI while ignoring the spectral data. In that way, it exhibits poor performance. As a result, spectral feature extraction now plays a big role in HSI data processing. Out of the several existing strategies for HSI spectral feature extraction, the discrete wavelet transform (DWT) approach is selected for analysis as a solution to the issue. Because it preserves the contrast between spectral signatures, spectral feature extraction using Wavelet Decomposition might be helpful. This work analyses two basic DWTs, namely Haar and Daubechies wavelets for this topic and gives a thorough examination of deep learning-based HSI categorization. In this regard, this paper examines the concept of wavelet CNN which highlights spectral characteristics by layering DWTs. The 2D CNN is next connected to the retrieved spectral features. It highlights spatial characteristics and generates a spatial spectral feature vector for classification. In particular, factor analysis is utilised to minimise the HSI dimension first. The discrete wavelet decomposition algorithm is then used to get four-level decomposition features. They are concatenated with 4-layer convolution features for merging spatial and spectral information, respectively. The entire approach aims to improve the final performance of the HSI classification with appropriate choice of mother wavelet. Experiments with wavelet feature fusion CNN on benchmark data sets like Indian Pines were conducted to assess the performance. To determine the overall classification accuracy, the classification results were analysed. In the context of extracting spectral features, it is discovered that Daubechies wavelets perform better in terms of classification than Haar wavelets.

With the continuous innovation in deep learning, it has become a major direction for scholars to introduce the knowledge of deep learning into hyperspectral image classification to enhance its classification accuracy. Convolutional Neural Networks (CNN) are one of the most commonly used deep learning-based visual data processing methods, and are widely used in hyperspectral image (HSI) classification by virtue of their excellent contextual modeling capability. Since the performance of HSI classification is highly dependent on spatial and spectral information, this paper proposes a hyperspectral image classification method using 3D attention mechanism in collaboration with Transformer for hyperspectral image classification in view of the problems that the current hyperspectral image classification models with the framework of CNN have insufficient spatial spectral feature extraction and fail to excavate and represent the sequence properties of spectral features well. In this paper, we introduce a variant Transformer model based on a hybrid model of both improved 3D-CNN and 2D-CNN, combining complementary information of spatial spectrum and spectra in the form of 3D convolution and 2D convolution on CNN, and adding a variant attention mechanism module to strengthen spatial texture features, while combining grouped transfer Transformer to jump connection to enable the lower layer to better learn the upper layer features. Firstly, a variant channel attention mechanism is introduced on 3D-CNN to enhance the acquisition of spectral information of image features by 3D-CNN. Secondly, a variant spatial attention mechanism is introduced to enable 3D-CNN to better acquire the spatial information of hyperspectral images in the network, and subsequently the acquired spatial and spectral feature information is passed to 2D-CNN to enable it to better acquire local feature information. Finally, the acquired image feature information is passed to the variant Transformer model to make up for the fact that CNN can only acquire hyperspectral image features in local contexts, enabling it to better acquire global feature information on feature sequences. The experimental results show that the proposed model is experimented on two hyperspectral datasets, Indian Pines and Pavia University, and the overall classification accuracy (OA), average classification accuracy (AA), and Kappa coefficient reach up to 99.59%, 99.31%, and 99.45%, respectively, on the PU dataset, compared with the current cutting-edge techniques. The classification accuracy has been improved.

Hyperspectral images are widely used for classification due to its rich spectral information along with spatial information. To process the high dimensionality and high nonlinearity of hyperspectral images, deep learning methods based on convolutional neural network (CNN) are widely used in hyperspectral classification applications. However, most CNN structures are stacked vertically in addition to using a onefold size of convolutional kernels or pooling layers, which cannot fully mine the multiscale information on the hyperspectral images. When such networks meet the practical challenge of a limited labeled hyperspectral image dataset—i.e., “small sample problem”—the classification accuracy and generalization ability would be limited. In this paper, to tackle the small sample problem, we apply the semantic segmentation function to the pixel-level hyperspectral classification due to their comparability. A lightweight, multiscale squeeze-and-excitation pyramid pooling network (MSPN) is proposed. It consists of a multiscale 3D CNN module, a squeezing and excitation module, and a pyramid pooling module with 2D CNN. Such a hybrid 2D-3D-CNN MSPN framework can learn and fuse deeper hierarchical spatial–spectral features with fewer training samples. The proposed MSPN was tested on three publicly available hyperspectral classification datasets: Indian Pine, Salinas, and Pavia University. Using 5%, 0.5%, and 0.5% training samples of the three datasets, the classification accuracies of the MSPN were 96.09%, 97%, and 96.56%, respectively. In addition, we also selected the latest dataset with higher spatial resolution, named WHU-Hi-LongKou, as the challenge object. Using only 0.1% of the training samples, we could achieve a 97.31% classification accuracy, which is far superior to the state-of-the-art hyperspectral classification methods.

The hyperspectral image is a three-dimensional (3D) hypercube with spectral and spatial continuity. Traditional hyperspectral imaging (HSI) processing mainly focuses on spectral information. However, this paper proposed a new hybrid convolutional neural network (New-Hybrid-CNN) algorithm using HSI spectral-spatial joint information. We used the algorithm combined with HSI processing to classify the origin of Chinese wolfberry from Ningxia, Qinghai, Gansu, and Xinjiang. (1) Selecting the region of interest (ROI) over the raw HSI data as input; (2) Extracting spectral-spatial joint information from the hyperspectral stack information using homogeneous 3D convolution architecture with convolution kernels; (3) Then the depth separable convolution (DSC) was used to learn spatial information. This algorithm combined the advantages of 3D convolution and DSC, and it effectively extracted deep spectral-spatial joint information and made the architecture more lightweight. 3D convolutional neural network (3D-CNN), hybrid spectral convolutional neural network (HybridSN), and support vector machine (SVM) were established to compare with the proposed method. The proposed algorithm made full use of the HSI information while reducing the number of parameters and training time involved in the network, and improved the classification accuracy. The classification accuracy of wolfberry origin reached more than 99%. Therefore, the New-Hybrid-CNN classifier combined with HSI had the potential to classify wolfberry origin and food detection.

Hyperspectral image (HSI) and multispectral image (MSI) fusion, which fuses a low-spatial-resolution HSI (LR-HSI) with a higher resolution multispectral image (MSI), has become a common scheme to obtain high-resolution HSI (HR-HSI). This article presents a novel HSI and MSI fusion method (called as CNN-Fus), which is based on the subspace representation and convolutional neural network (CNN) denoiser, i.e., a well-trained CNN for gray image denoising. Our method only needs to train the CNN on the more accessible gray images and can be directly used for any HSI and MSI data sets without retraining. First, to exploit the high correlations among the spectral bands, we approximate the desired HR-HSI with the low-dimensional subspace multiplied by the coefficients, which can not only speed up the algorithm but also lead to more accurate recovery. Since the spectral information mainly exists in the LR-HSI, we learn the subspace from it via singular value decomposition. Due to the powerful learning performance and high speed of CNN, we use the well-trained CNN for gray image denoising to regularize the estimation of coefficients. Specifically, we plug the CNN denoiser into the alternating direction method of multipliers (ADMM) algorithm to estimate the coefficients. Experiments demonstrate that our method has superior performance over the state-of-the-art fusion methods.