Combining convolutional neural network and self-adaptive algorithm to defeat synthetic multi-digit text-based CAPTCHA

Wang, Ye; Huang, Yuanjiang; Wu, Zheng; Zhi, Zhou; Liu, Debin; Lu, Mi

doi:10.1109/icit.2017.7915494

Cited by 31 publications

(12 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural Network has been widely applied on computer vision tasks and natural language processing tasks [12]- [14]. And Convolutional Neural Network (CNN) has achieved a great success on outperforming many state-of-the-art algorithms over object classifi-cation and detection [15], semantic segmentation [16], scene reconstruction, and face recognition [17].…”

Section: Introductionmentioning

confidence: 99%

Dilated Fully Convolutional Neural Network for Depth Estimation from a Single Image

Li¹,

Hua²,

Liu³

et al. 2021

Adv. sci. technol. eng. syst. j.

Self Cite

View full text Add to dashboard Cite

Depth prediction plays a key role in understanding a 3D scene. Several techniques have been developed throughout the years, among which Convolutional Neural Network has recently achieved state-of-the-art performance on estimating depth from a single image. However, traditional CNNs suffer from the lower resolution and information loss caused by the pooling layers. And oversized parameters generated from fully connected layers often lead to a exploded memory usage problem. In this paper, we present an advanced Dilated Fully Convolutional Neural Network to address the deficiencies. Taking advantages of the exponential expansion of the receptive field in dilated convolutions, our model can minimize the loss of resolution. It also reduces the amount of parameters significantly by replacing the fully connected layers with the fully convolutional layers. We show experimentally on NYU Depth V2 datasets that the depth prediction obtained from our model is considerably closer to ground truth than that from traditional CNNs techniques.

show abstract

Section: Introductionmentioning

confidence: 99%

Dilated Fully Convolutional Neural Network for Depth Estimation from a Single Image

Li¹,

Hua²,

Liu³

et al. 2021

Adv. sci. technol. eng. syst. j.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Autonomous crack detection systems aid short‐term and long‐term inspections in terms of decreasing human involvement during their operation, resulting in lower cost, higher reliability, and system efficiency. Concurrent to these developments in computer‐vision techniques, there has been a resurgence of machine learning algorithms in a variety of fields, including image processing and pattern recognition (Hashemi & Abdelghany, ; Koziarski & Cyganek, ; Molina‐Cabello, Luque‐Baena, López‐Rubio, & Thurnhofer‐Hemsi, ; Nabian & Meidani, ; Sonka, Hlavac, & Boyle, ; Torres, Galicia, Troncoso, & Martínez‐Álvarez, ; Wang & Bai, ; Wang et al., ; Wang et al, ; Wu, Zhang, Story, & Rajan, ; Zhang & Zhang, ). Meanwhile, the hardware implementation of training large‐scale neural networks also receives wide attention (Ortega‐Zamorano, Jerez, Gómez, & Franco, ).…”

Section: Introductionmentioning

confidence: 99%

Concrete crack detection using context‐aware deep semantic segmentation network

Zhang

Rajan

Story

2019

Computer aided Civil Eng

161

View full text Add to dashboard Cite

Computer‐vision and deep‐learning techniques are being increasingly applied to inspect, monitor, and assess infrastructure conditions including detection of cracks. Traditional vision‐based methods to detect cracks lack accuracy and generalization to work on complicated infrastructural conditions. This paper presents a novel context‐aware deep convolutional semantic segmentation network to effectively detect cracks in structural infrastructure under various conditions. The proposed method applies a pixel‐wise deep semantic segmentation network to segment the cracks on images with arbitrary sizes without retraining the prediction network. Meanwhile, a context‐aware fusion algorithm that leverages local cross‐state and cross‐space constraints is proposed to fuse the predictions of image patches. This method is evaluated on three datasets: CrackForest Dataset (CFD) and Tomorrows Road Infrastructure Monitoring, Management Dataset (TRIMMD) and a Customized Field Test Dataset (CFTD) and achieves Boundary F1 (BF) score of 0.8234, 0.8252, and 0.7937 under 2‐pixel error tolerance margin in CFD, TRIMMD, and CFTD, respectively. The proposed method advances the state‐of‐the‐art performance of BF score by approximately 2.71% in CFD, 1.47% in TRIMMD, and 4.14% in CFTD. Moreover, the averaged processing time of the proposed system is 0.7 s on a typical desktop with Intel® Quad‐Core™ i7‐7700 CPU@3.6 GHz Processor, 16GB RAM and NVIDIA GeForce GTX 1060 6GB GPU for an image of size 256 × 256 pixels.

show abstract

“…Neural Network has been widely applied on computer vision tasks and natural language processing tasks [12] [13] [14]. And Convolutional Neural Network (CNN) has achieved a great success on outperforming many state-of-the-art algorithms over object classification and detection [15], semantic segmentation [16], scene reconstruction, and face recognition [17].…”

Section: Introductionmentioning

confidence: 99%

Mitigating Congestion in Restructured Power System using FACTS Allocation by Sensitivity Factors and Parameter Optimized by GWO

Gautam¹,

Sharma²,

Kumar³

2020

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

In modern deregulated power industry, private sector has invested a lot to supply for extended power demand using the preexisting power system framework. This resulted into increased loading of transmission lines which has to work now to hit their thermal limits. The overloading of transmission line resulted in congestion and hence increase in loss of power in the system. One of the efficient ways to reduce congestion is by enhancing the available transfer capacity (ATC) of the power system. ATC enhancement can be achieved by application of FACTS devices. This paper presents an innovative method to mitigate congestion by locating TCSC in the IEEE 30 bus system. The allocation of TCSC is done by using ACPTDF sensitivity factors while the parameter setting is done by applying Grey Wolf Optimization (GWO) method. The effective application of GWO is demonstrated in this paper to reduce active power loss, enhancement of ATC value with reduction of reactive power loss and to optimize TCSC size through a multi objective function. The suitability of algorithm is established through concerned figures and tables.

show abstract

Combining convolutional neural network and self-adaptive algorithm to defeat synthetic multi-digit text-based CAPTCHA

Cited by 31 publications

References 14 publications

Dilated Fully Convolutional Neural Network for Depth Estimation from a Single Image

Dilated Fully Convolutional Neural Network for Depth Estimation from a Single Image

Concrete crack detection using context‐aware deep semantic segmentation network

Mitigating Congestion in Restructured Power System using FACTS Allocation by Sensitivity Factors and Parameter Optimized by GWO

Contact Info

Product

Resources

About