Enhancement of Image Classification Using Transfer Learning and GAN-Based Synthetic Data Augmentation (original) (raw)

Deep transfer learning benchmark for plastic waste classification

Intelligence & Robotics, 2022

Millions of people throughout the world have been harmed by plastic pollution. There are microscopic pieces of plastic in the food we eat, the water we drink, and even the air we breathe. Every year, the average human consumes 74,000 microplastics, which has a significant impact on their health. This pollution must be addressed before it has a significant negative influence on the population. This research benchmarks six state-of-the-art convolutional neural network models pre-trained on the ImageNet Dataset. The models Resnet-50, ResNeXt, MobileNet_v2, DenseNet, SchuffleNet and AlexNet were tested and evaluated on the WaDaBa plastic dataset, to classify plastic types based on their resin codes by integrating the power of transfer learning. The accuracy and training time for each model has been compared in this research. Due to the imbalance in the data, the undersampling approach has been used. The ResNeXt model attains the highest accuracy in fourteen minutes.

Dual-Branch CNN for the Identification of Recyclable Materials

2021

The classification of recyclable materials, and in particular the recovery of plastic, plays an important role in the economy, but also in environmental sustainability. This study presents a novel image classification model that can be efficiently used to distinguish recyclable materials. Building on recent work in deep learning and waste classification, we introduce the so-called “Dual-branch Multi-output CNN”, a custom convolutional neural network composed of two branches aimed to i) classify recyclables and ii) distinguish the type of plastic. The proposed architecture is composed of two classifiers trained on two different datasets, so as to encode complementary attributes of the recyclable materials. In our work, the Densenet121, ResNet50 and VGG16 architectures were used on the Trashnet dataset, along with data augmentation techniques, as well as on the WaDaBa dataset with physical variation techniques. In particular, our approach makes use of the joint utilization of the data...

Fruit quality and defect image classification with conditional GAN data augmentation

Scientia Horticulturae, 2022

Contemporary Artificial Intelligence technologies allow for the employment of Computer Vision to discern good crops from bad, providing a step in the pipeline of selecting healthy fruit from undesirable fruit, such as those which are mouldy or gangrenous. State-of-the-art works in the field report high accuracy results on small datasets (<1000 images), which are not representative of the population regarding real-world usage. The goals of this study are to further enable real-world usage by improving generalisation with data augmentation as well as to reduce overfitting and energy usage through model pruning. In this work, we suggest a machine learning pipeline that combines the ideas of fine-tuning, transfer learning, and generative model-based training data augmentation towards improving fruit quality image classification. A linear network topology search is performed to tune a VGG16 lemon quality classification model using a publicly-available dataset of 2690 images. We find that appending a 4096 neuron fully connected layer to the convolutional layers leads to an image classification accuracy of 83.77%. We then train a Conditional Generative Adversarial Network on the training data for 2000 epochs, and it learns to generate relatively realistic images. Grad-CAM analysis of the model trained on real photographs shows that the synthetic images can exhibit classifiable characteristics such as shape, mould, and gangrene. A higher image classification accuracy of 88.75% is then attained by augmenting the training with synthetic images, arguing that Conditional Generative Adversarial Networks have the ability to produce new data to alleviate issues of data scarcity. Finally, model pruning is performed via polynomial decay, where we find that the Conditional GAN-augmented classification network can retain 81.16% classification accuracy when compressed to 50% of its original size.

Classification of Waste Materials using CNN Based on Transfer Learning

Proceedings of the 14th Annual Meeting of the Forum for Information Retrieval Evaluation

Waste Management is important for humans as well as nature for healthy life and a clean environment. The major step for effective waste management is the segregation of waste according to its types. The advancement of technology such as hardware and artificial intelligence is used for the segregation of waste. There are several machine learning and deep learning algorithms available for image classification. Among them, Convolutional Neural Network is the most used one. The main objective of this work is to classify images of waste materials using CNN into seven categories (cardboard, glass, metal, organic, paper, plastic, and trash). Then, cardboard, organic, and paper class images are considered biodegradable waste, and other classes are considered non-biodegradable waste. The pre-trained CNN model such as InceptionV3, InceptionRes-NetV2, Xception, VGG19, MobileNet, ResNet50 and DenseNet201 have been trained and performed fine-tuning on the waste dataset. Among these models, the VGG19 model performed with less accuracy, whereas the InceptionV3 model performed with high learning accuracy. Overall, the obtained result is promising.

Recent Advances of Generative Adversarial Networks in Computer Vision

IEEE Access, 2018

The appearance of generative adversarial networks (GAN) provides a new approach and framework for computer vision. Compared with traditional machine learning algorithms, GAN works via adversarial training concept and is more powerful in both feature learning and representation. GAN also exhibits some problems, such as non-convergence, model collapse, and uncontrollability due to high degree of freedom. How to improve the theory of GAN and apply it to computer-vision-related tasks have now attracted much research efforts. In this paper, recently proposed GAN models and their applications in computer vision are systematically reviewed. In particular, we firstly survey the history and development of generative algorithms, the mechanism of GAN, its fundamental network structures, and theoretical analysis of the original GAN. Classical GAN algorithms are then compared comprehensively in terms of the mechanism, visual results of generated samples, and Frechet Inception Distance. These networks are further evaluated from network construction, performance, and applicability aspects by extensive experiments conducted over public datasets. After that, several typical applications of GAN in computer vision, including high-quality samples generation, style transfer, and image translation, are examined. Finally, some existing problems of GAN are summarized and discussed and potential future research topics are forecasted. INDEX TERMS Deep learning, generative adversarial networks (GAN), computer vision (CV), image generation, style transfer, image inpainting.

JGAN: A Joint Formulation of GAN for Synthesizing Images and Labels

IEEE Access

Image generation with explicit condition or label generally works better than unconditional methods. In modern GAN frameworks, both generator and discriminator are formulated to model the conditional distribution of images given with labels. In this article, we provide an alternative formulation of GAN which models the joint distribution of images and labels. There are two advantages in this joint formulation over conditional approaches. The first advantage is that the joint formulation is more robust to label noises if it's properly modeled. This alleviates the burden of making noise-free labels and allows the use of weakly-supervised labels in image generation. The second is that we can use any kinds of weak labels or image features that have correlations with the original image data to enhance unconditional image generation. We will show the effectiveness of our joint formulation on CIFAR10, CIFAR100, and STL dataset with the state-of-the-art GAN architecture. INDEX TERMS Deep learning, image synthesis, generative adversarial network.

The generative adversarial networks and its application in machine vision

Enterprise Information Systems, 2019

In recent years, the model of improved GAN has been widely applied in the field of machine vision. It not only covers the traditional image processing, but also includes image conversion, image synthesis and so on.. Firstly, this paper describes the basic principles and existing problems of GAN, then introduces several improved GAN models, including Info-GAN, DC-GAN, f-GAN, Cat-GAN and others. Secondly, several improved GAN models for different applications in the field of machine vision are described. Finally, the future trend and development of GAN are prospected.

Scope of generative adversarial networks (GANs) in image processing

International journal of health sciences

Generative Adversarial Network is the topic of interest in today’s research in the field of image processing and computer vision. A basic GAN model was introduced by Ian Goodfellow et al. in 2014. After that advancement in the field of research in GAN models has been application specific. In computer vision and image to image translation GANs are playing very effective role either in the case of face detection and recognition or in image resolution enhancement and image augmentation. This paper represents a concise overview of various GAN models along with their features and applications. Pix2Pix and conditional GAN models work upon paired datasets while other models like cycle GAN, discover GAN, dual GAN, info GAN, deep convolutional GAN etc. work upon unpaired datasets. Various image datasets which are commonly used for training of generator and discriminator networks are also discussed in this paper. Since partial mode collapse is a common problem to occur during training process...

Reach on Waste Classification and Identification by Transfer Learning and Lightweight Neural Network

2020

Using machine learning or deep learning to solve the problem of garbage recognition and classification is an important application in computer vision, but due to the incomplete establishment of garbage datasets and the poor performance of complex network models on smart terminal devices, the existing garbage classification models The effect is not good.This paper presents a waste classification and identification method base on transfer learning and lightweight neural network. By migrating the lightweight neural network MobileNetV2 and rebuild it, The reconstructed network is used for feature extraction, and the extracted features are introduced into the SVM to realize the identification of 6 types of garbage. The model was trained and verified by using 2527 pieces of garbage labeled data in the TrashNet dataset, which ultimately resulted in a classification accuracy of 98.4% of the method, which proves that the method can effectively improve the classification accuracy and time and...

Enhancing Object Segmentation Model with GAN-based Augmentation using Oil Palm as a Reference

2024

In digital agriculture, a central challenge in automating drone applications in the plantation sector, including oil palm, is the development of a detection model that can adapt across diverse environments. This study addresses the feasibility of using GAN augmentation methods to improve palm detection models. For this purpose, drone images of young palms (< 5 year-old) from eight different estates were collected, annotated, and used to build a baseline detection model based on DETR. StyleGAN2 was trained on the extracted palms and then used to generate a series of synthetic palms, which were then inserted into tiles representing different environments. CycleGAN networks were trained for bidirectional translation between synthetic and real tiles, subsequently utilized to augment the authenticity of synthetic tiles. Both synthetic and real tiles were used to train the GAN-based detection model. The baseline model achieved precision and recall values of 95.8% and 97.2%, whereas the GAN-based model achieved precision and recall values of 98.5% and 98.6%. In the challenge dataset 1 consisting older palms (> 5 year-old), both models also achieved similar accuracies, with baseline model achieving precision and recall of 93.1% and 99.4%, and GAN-based model achieving 95.7% and 99.4%. As for the challenge dataset 2 consisting of storm affected palms, the baseline model achieved precision of 100% but recall was only 13%, whereas GAN-based model achieved a high precision and recall values of 98.7% and 95.3%. This result demonstrates that images generated by GANs have the potential to enhance the accuracies of palm detection models.