Fruit Image Classification Using Deep Learning

Gill, Harmandeep Singh; Khalaf, Osamah Ibrahim; Alotaibi, Youseef; Alghamdi, Saleh; Alassery, Fawaz

doi:10.32604/cmc.2022.022809

Cited by 42 publications

(11 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, the authors in [ 36 ] used VGG-19 to detect cataracts by using color fundus images. Researchers in [ 37 ] investigated the principles of experimentation involved in evaluating the various methods. The authors in [ 38 ] implemented the study of various deep learning models for eye disease detection where several optimizations were performed.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning for Ocular Disease Recognition: An Inner-Class Balance

Khan

Tafshir

Alam

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

It can be challenging for doctors to identify eye disorders early enough using fundus pictures. Diagnosing ocular illnesses by hand is time-consuming, error-prone, and complicated. Therefore, an automated ocular disease detection system with computer-aided tools is necessary to detect various eye disorders using fundus pictures. Such a system is now possible as a consequence of deep learning algorithms that have improved image classification capabilities. A deep-learning-based approach to targeted ocular detection is presented in this study. For this study, we used state-of-the-art image classification algorithms, such as VGG-19, to classify the ODIR dataset, which contains 5000 images of eight different classes of the fundus. These classes represent different ocular diseases. However, the dataset within these classes is highly unbalanced. To resolve this issue, the work suggested converting this multiclass classification problem into a binary classification problem and taking the same number of images for both classifications. Then, the binary classifications were trained with VGG-19. The accuracy of the VGG-19 model was 98.13% for the normal (N) versus pathological myopia (M) class; the model reached an accuracy of 94.03% for normal (N) versus cataract (C), and the model provided an accuracy of 90.94% for normal (N) versus glaucoma (G). All of the other models also improve the accuracy when the data is balanced.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Learning for Ocular Disease Recognition: An Inner-Class Balance

Khan

Tafshir

Alam

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…When the keys are pressed, the felt-covered hammers are in contact with a set of strings. e key is combined with an escapement that allows the hammer to detach from the key before striking the string and return to its original position immediately after the impact [23,24]. e strings are unimpeded from the hammer.…”

Section: Piano Pronunciation Principlementioning

confidence: 99%

The Timbre Relationship between Piano Performance Skills and Piano Combined with Opera Music Elements in the Context of the Internet of Things

Deng

2022

Security and Communication Networks

View full text Add to dashboard Cite

The “quintessence of the nation” Peking Opera is a highly comprehensive form of opera, which has a high artistic status in traditional Chinese culture. At present, the combination of the Internet of things and music can be embodied in smart devices, through a computing device that can perceive and exchange data for the purpose of music. In the more than 100 years of development of the piano art in China, many composers have used Peking Opera singing and board styles, or absorbed the essence and connotation of Peking Opera, taking Peking Opera elements as the core material and source of creation and presenting them instrumentally through piano works. For example, in terms of smart musical instruments, the Internet of things and Internet technology are combined to realize the real-time connection between the remote piano and the piano and accurately reproduce all the touch and pedal movements of the player, so that teachers and students in different spaces can listen to the course. Audiences had an immersive course experience. Taking this as an opportunity, we will carry out a series of “remote art education” such as remote master classes and remote concerts, to realize the sharing of educational resources around the world. The piano as the king of musical instruments has been loved by people. During piano performance, touch key techniques and pedaling techniques have a very important influence on the piano’s performance sound effects. Chinese opera is the essence of Chinese national art and one of the treasures of China’s traditional national music. The composers of our country also constantly apply the opera elements to the piano creation and create many kinds of piano works that conform to the traditional Chinese opera style and reflect the characteristics of the piano. Pedal skills are also an important technique in piano performance. The pedaling method is based on thinking about history and showing the player’s intentions. Only using the correct playing skills can make the music more expressive. This study briefly introduces the development of piano in China and the playing skills of the piano, and at the same time, it briefly describes the principle of piano sounding and the sound of piano. Based on the previous studies, the effects of touch key techniques and pedaling techniques on the sound of the piano are discussed. I hope to provide some references for the piano performers. The average similarity between the final music and the original music is 60% and around 70%. This article provides a reference direction for the diversified dissemination and promotion of theatrical art and provides theoretical and technical reference suggestions for the future creation, performance, and teaching of Chinese piano music.

show abstract

“…With the rapid development of artificial intelligence, several swarm intelligence algorithms have been developed to optimize neural networks for their powerful global optimisation capability and faster convergence speed to improve the generalization performance of networks [20].…”

Section: Introductionmentioning

confidence: 99%

Intelligent Evaluation of Product Form Design Based on Deep Neural Network Model

Wang

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In order to evaluate the product morphological design, a method of applying BP neural network to evaluate the product morphological design is proposed based on the analysis of the principle of artificial neural network. In such method, the advantages of the BP neural network with self-learning, self-organization, self-adaptation, and nonlinear dynamic processing are applied to effectively evaluate the product morphological design. Specifically, 13 product morphological design solutions of the automotive evaluation data set are selected as samples, 15 out of 18 solutions are used to train the evaluation system, and the remaining 3 solutions are used to validate the trained system. The validation results show that the relative errors between the simulated and actual values are 3.6%, −1.7%, and 2.8%, respectively. Such results also show high accuracy and simultaneously can reflect the effectiveness of our proposed system for evaluating the design solutions.

show abstract

Fruit Image Classification Using Deep Learning

Cited by 42 publications

References 31 publications

Deep Learning for Ocular Disease Recognition: An Inner-Class Balance

Deep Learning for Ocular Disease Recognition: An Inner-Class Balance

The Timbre Relationship between Piano Performance Skills and Piano Combined with Opera Music Elements in the Context of the Internet of Things

Intelligent Evaluation of Product Form Design Based on Deep Neural Network Model

Contact Info

Product

Resources

About