Classification of photographed document images based on deep-learning features

Zhong, Guoqiang; Yao, Hui; Liu, Yutong; Chen, Hong; Pham, Tuan D.

doi:10.1117/12.2266984

Cited by 5 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Table 1, several popular CNN architectures, such as AlexNet [32], VGGNet [33], and ResNet [34], have been widely used in research. We experimented with various architectures to investigate the applicability and usability of our dataset and report all results to provide an in depth review of the applicability and limitations of the proposed dataset.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Identification of Single Bacterial Colonies Using Deep and Transfer Learning

et al. 2022

View full text Add to dashboard Cite

Bacterial classification is a vital step in medical diagnosis. This procedure normally has several stages. An early stage involves inspecting the morphology of the bacterial colonies. Traditionally, a bacterial colony expert inspects the sample to determine the type of bacteria through visual inspection or molecular biology techniques. With advances in image processing, specifically, the use of deep and transfer learning techniques, and the wide availability of cameras, we applied deep and transfer learning techniques to address this task without requiring expert knowledge or sample shipping. We used a convolutional neural network (CNN) to identify different bacterial colonies based on their appearance in images captured by cell phone cameras. In this paper, we collected a dataset that contains images of different bacteria taken by cell phone cameras with various settings. Thus, images of two classes of bacterial colonies were obtained in King Abdulaziz City for Science and Technology. The dataset contains 8,043 images. The experimental results show that our application has high accuracy without requiring expert inspections.

show abstract

Section: Related Workmentioning

confidence: 99%

“…We used five CNN architectures: ResNet-18 [38], AlexNet [32], VGG-16 [33], SqueezeNet [39], and DenseNet 161 [40]. All models were pretrained on the 1000-class ImageNet dataset [41].…”

Section: Experiments a System Setups And Model Parametersmentioning

confidence: 99%

Automatic Identification of Single Bacterial Colonies Using Deep and Transfer Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Accordingly, this feature was called deep convolutional activation feature (DeCAF). In [95] Recently, the deep learning models obtained much attention are recurrent neural networks (RNNs) [79,97], long short-term memory (LSTM) [98,99], attention based models [100,101] and generative adversarial nets [102]. The applications are generally focused on image classification, object detection, speech recognition, handwriting recognition, image caption generation and machine translation [103,104,105].…”

Section: Deep Learning Modelsmentioning

confidence: 99%

An overview on data representation learning: From traditional feature learning to recent deep learning

Zhong

Wang

Ling

et al. 2016

The Journal of Finance and Data Science

161

View full text Add to dashboard Cite

Since about 100 years ago, to learn the intrinsic structure of data, many representation learning approaches have been proposed, including both linear ones and nonlinear ones, supervised ones and unsupervised ones. Particularly, deep architectures are widely applied for representation learning in recent years, and have delivered top results in many tasks, such as image classification, object detection and speech recognition. In this paper, we review the development of data representation learning methods.Specifically, we investigate both traditional feature learning algorithms and state-ofthe-art deep learning models. The history of data representation learning is introduced, while available resources (e.g. online course, tutorial and book information) and toolboxes are provided. Finally, we conclude this paper with remarks and some interesting research directions on data representation learning.

show abstract

“…They tend to use multiple learning algorithms for better predictive performance compared with any other constituent learning algorithms alone [2][3][4][5]. In particular, even the deep learning models that have already successfully applied in many fields [6][7][8][9], are also popular to use the idea of ensemble learning for improving their performance [10][11][12][13]. For instance, some work adopts the ensemble of deep networks to perform classification or detection tasks [14,15].…”

Section: Introductionmentioning

confidence: 99%

Random Shapley Forests: Cooperative Game-Based Random Forests With Consistency

Sun

Zhong

et al. 2022

IEEE Trans. Cybern.

Self Cite

View full text Add to dashboard Cite

The original random forests algorithm has been widely used and has achieved excellent performance for the classification and regression tasks. However, the research on the theory of random forests lags far behind its applications. In this paper, to narrow the gap between the applications and theory of random forests, we propose a new random forests algorithm, called random Shapley forests (RSFs), based on the Shapley value. The Shapley value is one of the well-known solutions in the cooperative game, which can fairly assess the power of each player in a game. In the construction of RSFs, RSFs uses the Shapley value to evaluate the importance of each feature at each tree node by computing the dependency among the possible feature coalitions. In particular, inspired by the existing consistency theory, we have proved the consistency of the proposed random forests algorithm. Moreover, to verify the effectiveness of the proposed algorithm, experiments on eight UCI benchmark datasets and four real-world datasets have been conducted. The results show that RSFs perform better than or at least comparable with the existing consistent random forests, the original random forests and a classic classifier, support vector machines.

show abstract

Classification of photographed document images based on deep-learning features

Cited by 5 publications

References 6 publications

Automatic Identification of Single Bacterial Colonies Using Deep and Transfer Learning

Automatic Identification of Single Bacterial Colonies Using Deep and Transfer Learning

An overview on data representation learning: From traditional feature learning to recent deep learning

Random Shapley Forests: Cooperative Game-Based Random Forests With Consistency

Contact Info

Product

Resources

About