A Survey: Image Classification Models Based on Convolutional Neural Networks

Peng, Luzhou; Qiang, Bowen; Wu, Jiacheng

doi:10.1109/iccrd54409.2022.9730565

Cited by 5 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By combining multiple levels of representation, it becomes possible to learn complex functions [1]. Image classification algorithms are utilized to determine the category to which an input image belongs [2]. The accuracy of image classification can be enhanced by utilizing deep learning, which involves creating machine learning models with multiple hidden layers and training them with extensive amounts of data.…”

Section: Introductionmentioning

confidence: 99%

Comparative Study of Deep Learning Neural Networks for Image Classification

Huang

2023

HSET

View full text Add to dashboard Cite

Image classification plays a crucial role in image recognition in present times. Researchers have developed numerous methods for achieving image classification through long-term research. Deep Learning, as one of the most important methodologies, is used to clarify the contents of an image. This paper provides an overview of four typical deep learning neural networks used for image classification, including conventional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), and deep neural networks (DNN). The architecture, function, and applications of each network are discussed and compared. CNN is commonly used for image recognition, while RNN is suitable for speech recognition, natural language processing, and time series forecasting. DNN is ideal for handling high-dimensional data, and GAN can generate new data samples. The StyleGAN is introduced as an application of GAN, which can produce high-quality images. Finally, the future work and challenges in image recognition are discussed.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparative Study of Deep Learning Neural Networks for Image Classification

Huang

2023

HSET

View full text Add to dashboard Cite

show abstract

“…Like TensorFlow Lite Model Maker, PyTorch Mobile provides a simple way to adapt and convert machine learning models for deployment on mobile devices. "This paper[1] presents a survey on image classification models based on convolution neural networks (CNNs).…”

mentioning

confidence: 99%

“Dataset to Model: Optimization of Image Classification With Neural Networks”

Sharma,

Sekhar

2023

IJEAST

View full text Add to dashboard Cite

The field of computer vision has seen rapid growth in recent years, with image classification being one of the fundamental tasks within the field. In image classification, a ‘machine learning algorithm’ is trained to identify and categorize objects within an image. Such Pre-trained models can be used to save time and computational resources, as the model has already learned to extract useful features from the data. Efficient Net-Lite models, MobileNetV2, and ResNet50 are some of the pre-trained learning models that are used for image classification tasks. Tensor Flow Lite Model Maker is a library developed by Open AI that simplifies the process of adapting a model to specific input data, which is necessary when deploying the model to run on a device. The library can be used to convert a Tensor Flow model into a format that can be run on a mobile device, such as a smartphone or tablet. This paper presents a study on the optimization of image classification using neural networks. The study utilizes a dataset to train a neural network model and investigate the impact of various parameters on the accuracy of the model. The dataset is preprocessed to remove any outliers and ensure the quality of the data. The neural network model is then optimized through the use of different architectures and hyper parameters. The study shows that the accuracy of the model can be improved through the use of various optimization techniques. Overall, this research contributes to the growing body of knowledge on the optimization of image classification using neural networks, and provides insights on how to effectively train a model for improved accuracy.”

show abstract