Image Classification Using Deep Neural Network

Tiwari, V.; Pandey, Chandrasen; Dwivedi, Ankita; Yadav, Vrinda

doi:10.1109/icacccn51052.2020.9362804

Cited by 34 publications

(10 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study of animal species image classification (Tiwari, 2020) has previously been done by many researchers (Prudhivi, 2021). With the images, this study tried to classify them with the CNN process and with the reference datasets, this study does pixels mean processing to the images.…”

Section: Methodsmentioning

confidence: 99%

Classification of Animal Images with modified CNN model

Jana¹

2022

Preprint

View full text Add to dashboard Cite

In the age of modern artificial intelligence, new methodologies are evolving day by day for species classification. There is some need for categorization of the animal for the preservation and restoration of species. Due to this, there are several techniques for the identification of animals out of the deep learning methods that are most useful for animal classification for their images. In this study, the modified and improved convolution neural network (CNN) has been employed. This study is the identification methodologies of the ten animals which are cat, dog, tiger, lion, sheep, rhino, cheetah, elephant, squirrel, and panda. These animals need to be identified by the artificial intelligence-based system for the large-scale preservation system and the accuracy obtained by the modified CNN is this. In the future, this study is going to evolve deep learning for human-less classification systems and this study will maintain the balance between the machine and animals in restricted areas that humans can't reach there. Animal classification is one of the core problems in Computer vision. A lot of attention has been associated with Deep Learning, specifically neural networks such as CNN. This animal classification model gives some accuracy of 95%.

show abstract

Section: Methodsmentioning

confidence: 99%

Classification of Animal Images with modified CNN model

Jana¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Initially, a CNN was developed for computer vision, where a two-dimensional image database was analysed for classification-related applications [79]. A CNN is a special form of a multi-layer neural network.…”

Section: Description Of Cnn Modelmentioning

confidence: 99%

Frame Boundary Detection and Deep Learning-Based Doppler Shift Estimation for FBMC/OQAM Communication System in Underwater Acoustic Channels

Kotipalli¹,

Mohanraju²,

Vardhanapu³

2022

IEEE Access

View full text Add to dashboard Cite

Underwater acoustic (UWA) communication is the only option for underwater long-distance wireless communication. However, its data rate is very low, in tens of kbps, and the time-varying nature of the UWA channel exhibits a Doppler effect. The data rate can be increased using a multicarrier technique, such as Filter Bank Multicarrier (FBMC). The FBMC-OQAM system does not require a cyclic prefix (CP) to eliminate intersymbol interference (ISI). Therefore, compared to other multicarrier techniques, the FBMC-OQAM system achieves the maximum spectral efficiency. Despite the well-designed filter, synchronisation errors cause performance degradation in the FBMC-OQAM system. In this paper, we propose frame boundary and Doppler frequency estimation methods for the FBMC-OQAM system under UWA channels.In this study, we propose a preamble-based frame boundary. The conjugate symmetry property is used in the frame boundary estimation. The performance of the proposed technique was studied under different UWA channels with different Doppler scale. The proposed time synchronisation technique yielded multiple peaks under UWA channels. A method for identifying the peak that represents the frame boundary is proposed. We compared the performance of proposed timing metric with Schmidl & Cox timing metric and Reddy"s timing metric. The proposed timing metric exhibited superior performance over existing techniques. In addition, we propose a convolutional neural network (CNN)-based Doppler scale estimation method. The proposed technique was shown to estimate a wide range of Doppler scale factors. The performance of the proposed technique was studied by considering different UWA channels at different SNRs. The proposed CNN architecture is analysed by changing the CNN parameters. Stacked autoencoders were adopted for Doppler scale estimation and the performance of the proposed CNN-based Doppler scale estimation method was compared with the stacked autoencoders based Doppler scale estimation method. Simulation results show that the proposed CNN-based Doppler Scale estimator exhibits good performance in UWA channels at different SNRs and Doppler scale factors.

show abstract

“…V. Tiwari et al, (2020) [7] uses VGC16 as pre-trained model to achieve image classification. It compares its results with different models such as Baseline CNN, three block VGG model.…”

Section: Literature Reviewmentioning

confidence: 99%

Survey paper on Hand Gesture Recognition Based Virtual Mouse

Waichal¹

2022

IJSREM

View full text Add to dashboard Cite

Abstract—The invention of computer has been a turning point in the history. It makes our day-to-day life much simpler. The way to communicate with computer i.e., Human Computer Interaction (HCI), is through input and output devices. Mouse is one of the input devices. Mouse is an important part of Human Computer Interaction (HCI). With evolving technology, the cursor can be controlled without physical mouse hardware but using tip of a finger, hand gestures, etc. These hand movements can be recorded through webcam. The movement of the cursor can also be controlled by color detection or fingertip tracking using a webcam. This new era technology is useful in many fields, in many situations. This can be accomplished using extra hardware component or developing a software system. This is achieved through various image processing techniques and gesture recognition techniques without extra hardware. In this paper we have proposed a system which uses hand gesture recognition-based Convolutional Neural Network (CNN) model for controlling the mouse. Keywords—Virtual mouse, Hand Gesture Recognition, CNN model

show abstract

Image Classification Using Deep Neural Network

Cited by 34 publications

References 4 publications

Classification of Animal Images with modified CNN model

Classification of Animal Images with modified CNN model

Frame Boundary Detection and Deep Learning-Based Doppler Shift Estimation for FBMC/OQAM Communication System in Underwater Acoustic Channels

Survey paper on Hand Gesture Recognition Based Virtual Mouse

Contact Info

Product

Resources

About