Pest detection and classification to reduce pesticide use in fruit crops based on deep neural networks and image processing

2021 ◽  
Author(s):  
Agustina Suarez ◽  
Romina Soledad Molina ◽  
Giovanni Ramponi ◽  
Ricardo Petrino ◽  
Luciana Bollati ◽  
...  
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Deep Neural Networks ◽  
Pesticide Use ◽  
Fruit Crops ◽  
Pest Detection

scholarly journals COSMO: Computing with Stochastic Numbers in Memory

2022 ◽  
Vol 18 (2) ◽  
pp. 1-25
Author(s):  
Saransh Gupta ◽  
Mohsen Imani ◽  
Joonseop Sim ◽  
Andrew Huang ◽  
Fan Wu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Energy Efficient ◽  
Deep Neural Networks ◽  
Parallel Architecture ◽  
Low Energy ◽  
Stochastic Computing ◽  
Wide Range ◽  
Low Energy Consumption ◽  
Sc Addition

Stochastic computing (SC) reduces the complexity of computation by representing numbers with long streams of independent bits. However, increasing performance in SC comes with either an increase in area or a loss in accuracy. Processing in memory (PIM) computes data in-place while having high memory density and supporting bit-parallel operations with low energy consumption. In this article, we propose COSMO, an architecture for co mputing with s tochastic numbers in me mo ry, which enables SC in memory. The proposed architecture is general and can be used for a wide range of applications. It is a highly dense and parallel architecture that supports most SC encodings and operations in memory. It maximizes the performance and energy efficiency of SC by introducing several innovations: (i) in-memory parallel stochastic number generation, (ii) efficient implication-based logic in memory, (iii) novel memory bit line segmenting, (iv) a new memory-compatible SC addition operation, and (v) enabling flexible block allocation. To show the generality and efficiency of our stochastic architecture, we implement image processing, deep neural networks (DNNs), and hyperdimensional (HD) computing on the proposed hardware. Our evaluations show that running DNN inference on COSMO is 141× faster and 80× more energy efficient as compared to GPU.

scholarly journals Interactive Artistic Multi-style Transfer

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Xiaohui Wang ◽  
Yiran Lyu ◽  
Junfeng Huang ◽  
Ziying Wang ◽  
Jingyan Qin
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Deep Neural Networks ◽  
Subjective Evaluation ◽  
User Interaction ◽  
Evaluation Framework ◽  
Transfer System ◽  
Style Transfer ◽  
Artistic Style ◽  
Artistic Styles

AbstractArtistic style transfer is to render an image in the style of another image, which is a challenge problem in both image processing and arts. Deep neural networks are adopted to artistic style transfer and achieve remarkable success, such as AdaIN (adaptive instance normalization), WCT (whitening and coloring transforms), MST (multimodal style transfer), and SEMST (structure-emphasized multimodal style transfer). These algorithms modify the content image as a whole using only one style and one algorithm, which is easy to cause the foreground and background to be blurred together. In this paper, an iterative artistic multi-style transfer system is built to edit the image with multiple styles by flexible user interaction. First, a subjective evaluation experiment with art professionals is conducted to build an open evaluation framework for style transfer, including the universal evaluation questions and personalized answers for ten typical artistic styles. Then, we propose the interactive artistic multi-style transfer system, in which an interactive image crop tool is designed to cut a content image into several parts. For each part, users select a style image and an algorithm from AdaIN, WCT, MST, and SEMST by referring to the characteristics of styles and algorithms summarized by the evaluation experiments. To obtain richer results, the system provides a semantic-based parameter adjustment mode and the function of preserving colors of content image. Finally, case studies show the effectiveness and flexibility of the system.

scholarly journals Tessarine and Quaternion-Valued Deep Neural Networks for Image Classification

2021 ◽  
Author(s):  
Fernando Ribeiro de Senna ◽  
Marcos Eduardo Valle
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Image Classification ◽  
Deep Neural Networks ◽  
Real Numbers ◽  
Image Processing And Analysis ◽  
Batch Normalization

Many image processing and analysis tasks are performed with deep neural networks. Although the vast majority of advances have been made with real numbers, recent works have shown that complex and hypercomplex-valued networks may achieve better results. In this paper, we address quaternion-valued and introduce tessarine-valued deep neural networks, including tessarine-valued 2D convolutions. We also address initialization schemes and hypercomplex batch normalization. Finally, a tessarine-valued ResNet model with hypercomplex batch normalization outperformed the corresponding real and quaternion-valued networks on the CIFAR dataset.

scholarly journals Object Detection Based on Faster R-Cnn

2021 ◽  
Vol 10 (3) ◽  
pp. 72-76
Author(s):  
M. Sushma Sri ◽  
B. Rajendra Naik ◽  
K. Jaya Sankar
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Deep Learning ◽  
Object Detection ◽  
Deep Neural Networks ◽  
Rapid Development ◽  
Simple Algorithm ◽  
Average Precision ◽  
Rapid Improvement ◽  
High Level

In recent years there is rapid improvement in Object detection in areas of video analysis and image processing applications. Determing a desired object became an important aspect, so that there are many numerous of methods are evolved in Object detection. In this regard as there is rapid development in Deep Learning for its high-level processing, extracting deeper features, reliable and flexible compared to conventional techniques. In this article, the author proposes Object detection with deep neural networks and faster region convolutional neural networks methods for providing a simple algorithm which provides better accuracy and mean average precision.

scholarly journals Use of a trained denoising autoencoder to estimate the noise level in the ECG

2021 ◽  
Vol 7 (2) ◽  
pp. 562-565
Author(s):  
Fars Samann ◽  
Thomas Schanze
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Standard Deviation ◽  
Noise Level ◽  
Deep Neural Networks ◽  
Statistical Properties ◽  
Training Dataset ◽  
Effective Algorithm ◽  
Denoising Autoencoder ◽  
Noise Level Estimation

Abstract Noise level estimation plays an important role in many applications of signal and image processing, like denoising, compression and detection. Recently, deep neural networks have also been increasingly used for this purpose. In this paper, we develop an effective algorithm of noise level estimation of ECG segments based on trained denoising autoencoder (DAE) with a statistical thresholding method. An important observation is that a well-trained DAE model provides a clean representation of the corrupted training dataset. Two identical cascaded trained DAE models are considered to estimate the statistical properties, e.g., mean and standard deviation, from the trained DAE outputs after applying noise free aligned and jittered training dataset respectively. Two statistical thresholds are calculated from these statistical properties to classify whether the ECG segment is noise-free or jittered or noisy segment. The accuracy of the proposed method is quite promising in classifying and estimating unknow noise level.

Fast deep neural networks for image processing using posits and ARM scalable vector extension

2020 ◽  
Vol 17 (3) ◽  
pp. 759-771
Author(s):  
Marco Cococcioni ◽  
Federico Rossi ◽  
Emanuele Ruffaldi ◽  
Sergio Saponara
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Deep Neural Networks
Sign in / Sign up

Export Citation Format

Share Document