Convolutional Neural Networks in Visual Computing

Venkatesan, Ragav; Li, Baoxin

doi:10.4324/9781315154282

Cited by 94 publications

(48 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…σ 代表神经元的激活, w是权重, b称为偏差. f 表示非线性函数, 常用的非线性函数包括ReLU和Sigmoid函数 [66,67] : [68] 提出的 "新认知机 "(neocognitron)模型. 20世纪90年代, LeCun等人 [69,70] 确立了卷积神经网络的现代结构, 并不断对其完善.…”

Section: 权重神经元的值由上一层神经元的值与两层神经unclassified

Combination and application of machine learning and computational mechanics

Li¹,

Yan²,

Liu³

2019

Chin. Sci. Bull.

View full text Add to dashboard Cite

Section: 权重神经元的值由上一层神经元的值与两层神经unclassified

Combination and application of machine learning and computational mechanics

Li¹,

Yan²,

Liu³

2019

Chin. Sci. Bull.

View full text Add to dashboard Cite

“…Then, the subsequent layers try to combine them in simpler forms and, finally, in patterns of the different positions of the objects, lighting scales, etc. The final layers will try to match an input image with all the patterns and arrive at a final prediction as a weighted sum of all of them [20].…”

Section: • Lbp (Local Binary Pattern)mentioning

confidence: 99%

Diseases Detection in Blueberry Leaves using Computer Vision and Machine Learning Techniques

Sullca¹,

Molina²,

Rodríguez³

et al. 2019

IJMLC

View full text Add to dashboard Cite

This paper explains how image processing techniques and Machine Learning algorithms were used, such as Support Vector Machine (SVM), Artificial Neural Networks (ANN) and Random Forest; and Deep Learningś technique Convolutional Neural Network (CNN) was also used so we can determine which is the best algorithm for the construction of a recognition model that detects whether a blueberry plant is being affected by a disease or pest, or if it is healthy. The images were processed with different filters such as medianBlur and gaussianblur for the elimination of noise, the add Weighted filter was used for the enhancement of details in the images. The images were compiled by the authors of this work, since there was no accessible database of this specific kind of fruit, for which we visited Valle and Pampa farm so we could take pictures of different blueberry leaves, labeled in three different tags: diseased, plagued and healthy. The extraction of characteristics was done with algorithms such as HOG (Histogram of oriented gradients) and LBP (Local binary patterns), both normalized and not normalized. The results of the model showed an 84% accuracy index using Deep Learning, this model was able to classify whether the blueberry plant was being affected or not. The result of this work provides a solution to a constant problem in the agricultural sector that affects the production of blueberries, because pests as well as diseases are constant problems in this sector.

show abstract

“…Convolutional neural networks (CNNs, or ConvNets) are deep and feed-forward neural networks that are normally used in image analysis and classification [55]. In 1962, Hubel et al [24] studied the visual cortex of cats and monkeys, proposing the existence of a structure in the eyes of these animals called the receptive field.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…Their study also proposed the existence of two types of visual cells: simple cells, and complex cells. Simple cells detect straight edges with specific directions, whereas complex cells do not take the position of edges into consideration [55]. Based on these observations, Fukushima and Kunihiko [15] introduced the Neocognitron.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Object Detection and Tracking for Creation of Interactive Videos

Li¹

View full text Add to dashboard Cite

Interactive videos can help to draw audiences' attention to certain content in a video, resulting in a more appealing or intriguing type of video. Object detection is a fundamental approach that can be used to automatically create interactive videos. In this thesis, we propose a new method for object detection based on combining object recognition with tracking in a neural network. Specifically, we use GoogLeNet [51] as a feature extractor, and then apply a long short-term memory (LSTM) network to further adjust the feature vectors extracted by GoogLeNet according to the context of the feature vectors extracted from the previous frame. We feed the output of the LSTM to a classifier and regressor as in the Overfeat network [46], to obtain predicted confidences and predicted bounding boxes. We pre-train the feature extractor on images of the ImageNet [29] and Pascal Visual Object Classes (VOC) [14] datasets. We then evaluate our network on the visual tracker benchmark OTB100 [5], which is a dataset composed of videos with objects from a variety of classes. We use this dataset for training and testing our network. We compare our results to results obtained without tracking, where GoogLeNet [51] is only combined with the Overfeat network [46] for classification and regression. Our model shows a better performance at predicting objects in frames where occlusion and background clutter appear, and results in more consistent object bounding boxes across frames.

show abstract

Convolutional Neural Networks in Visual Computing

Cited by 94 publications

References 0 publications

Combination and application of machine learning and computational mechanics

Combination and application of machine learning and computational mechanics

Diseases Detection in Blueberry Leaves using Computer Vision and Machine Learning Techniques

Object Detection and Tracking for Creation of Interactive Videos

Contact Info

Product

Resources

About