Sketch recognition using transfer learning

Sert, Mustafa; Boyaci, Emel

doi:10.1007/s11042-018-7067-1

Cited by 21 publications

(20 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed scheme classification accuracy (72.93%) also beats the classification accuracy obtained by LeNet (55.2%) [17], HOG‐SVM (accuracy rate 56%) [3], sketch classification accuracy (61.5%) by Ensemble matching [22], Multi‐Kernel SVM (65.8%) [24], AlexNet‐SVM (67.1%) [14], and Fisher vector SP (68.9%) [9], in the literature study. Furthermore, the achieved results are also compared with most recent deep CNNs studies with classification accuracies (72.82%) [10], (72.5%) [18], and (69.17%) [19]. The proposed scheme also achieves competitive results as compared to human accuracy (73.1%) [3] for sketch recognition.…”

Section: Resultsmentioning

confidence: 88%

See 1 more Smart Citation

Entropy information‐based heterogeneous deep selective fused features using deep convolutional neural network for sketch recognition

Hayat

She

Shahzad

et al. 2021

IET Computer Vision

View full text Add to dashboard Cite

An effective feature representation can boost recognition tasks in the sketch domain. Due to an abstract and diverse structure of the sketch relatively with a natural image, it is complex to generate a discriminative features representation for sketch recognition. Accordingly, this article presents a novel scheme for sketch recognition. It generates a discriminative features representation as a result of integrating asymmetry essential information from deep features. This information is kept as an original feature‐vector space for making a final decision. Specifically, five different well‐known pre‐trained deep convolutional neural networks (DCNNs), namely, AlexNet, VGGNet‐19, Inception V3, Xception, and InceptionResNetV2 are fine‐tuned and utilised for feature extraction. First, the high‐level deep layers of the networks were used to get multi‐features hierarchy from sketch images. Second, an entropy‐based neighbourhood component analysis was employed to optimise the fusion of features in order of rank from multiple different layers of various deep networks. Finally, the ranked features vector space was fed into the support vector machine (SVM) classifier for sketch classification outcomes. The performance of the proposed scheme is evaluated on two different sketch datasets such as TU‐Berlin and Sketchy for classification and retrieval tasks. Experimental outcomes demonstrate that the proposed scheme brings substantial improvement over human recognition accuracy and other state‐of‐the‐art algorithms.

show abstract

Section: Resultsmentioning

confidence: 88%

“…Sert et al. [18] analyses different CNN architectures adapting the transfer learning approach for sketch recognition. In this framework, an early fusion of different layers using PCA for feature reduction and RBF‐SVM classifier was observed.…”

Section: Related Workmentioning

confidence: 99%

Entropy information‐based heterogeneous deep selective fused features using deep convolutional neural network for sketch recognition

Hayat

She

Shahzad

et al. 2021

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…e performance of the MSVM-based SKETRACK is evaluated on online diagram databases. e results obtained on FC and FA diagram instances are compared with that of three state-of-the-art methods: multiclass SVM [24,25], CNN [31], and CNN-SVM [37] while SVM [46,47] is only compared with the proposed MSVM results for the DLC diagrams due to lack of more existing methods. e two main reasons for the less research on DLC sketches and their limited capacity are as follows: (1) the complexity of the DLC sketches and (2) the inability to adapt with the quality of input employed.…”

Section: Comparison Of Sketrack Recognition Results With Other Methodsmentioning

confidence: 99%

“…is approach has better recognition performance due to the consideration of the unique properties of the sketches. In order to outperform Sketch-a-Net, Sert and Boyacı [37] proposed an efficient freehand sketch recognition approach using transfer learning models based on the feature-level fusion of CNN along with CNN-SVM pipeline architecture. e principal component analysis (PCA) is utilized to reduce the fused deep feature dimensions and increase the overall recognition accuracy to 73.1% on the TU-Berlin dataset [1] for smartphone applications.…”

Section: Related Workmentioning

confidence: 99%

SKETRACK: Stroke-Based Recognition of Online Hand-Drawn Sketches of Arrow-Connected Diagrams and Digital Logic Circuit Diagrams

Altun

Nooruldeen

2019

Scientific Programming

View full text Add to dashboard Cite

Digitalization of handwritten documents has created a greater need for accurate online recognition of hand-drawn sketches. However, the online recognition of hand-drawn diagrams is an enduring challenge in human-computer interaction due to the complexity in extracting and recognizing the visual objects reliably from a continuous stroke stream. This paper focuses on the design and development of a new, efficient stroke-based online hand-drawn sketch recognition scheme named SKETRACK for hand-drawn arrow diagrams and digital logic circuit diagrams. The fundamental parts of this model are text separation, symbol segmentation, feature extraction, classification, and structural analysis. The proposed scheme utilizes the concepts of normalization and segmentation to isolate the text from the sketches. Then, the features are extracted to model different structural variations of the strokes that are categorized into the arrows/lines and the symbols for effective processing. The strokes are clustered using the spectral clustering algorithm based on p-distance and Euclidean distance to compute the similarity between the features and minimize the feature dimensionality by grouping similar features. Then, the symbol recognition is performed using modified support vector machine (MSVM) classifier in which a hybrid kernel function with a lion optimized tuning parameter of SVM is utilized. Structural analysis is performed with lion-based task optimization for recognizing the symbol candidates to form the final diagram representations. This proposed recognition model is suitable for simpler structures such as flowcharts, finite automata, and the logic circuit diagrams. Through the experiments, the performance of the proposed SKETRACK scheme is evaluated on three domains of databases and the results are compared with the state-of-the-art methods to validate its superior efficiency.

show abstract

“…And the game stopped when it recognized the category of the drawing sketch which is the same as the category of the prompt by the system. In 2018, Sert [18] designed and implemented an application to identify sketches in smart devices. The application contained two modules: a sketch recognition program and a sketch application on mobile phones.…”

Section: Sketch Recognition Applicationsmentioning

confidence: 99%

LW-Sketch-Net on Mobile Phones

Kong¹,

Hu²,

Bai³

2019

EAI Endorsed Transactions on Creative Technologies

View full text Add to dashboard Cite

With the popularity of smart terminals, people tend to draw simple sketches to express emotions and ideas in communication, which means the era of reading pictures is coming. Therefore, in the field of sketch recognition, the application of deep network models in mobile devices is an irreversible trend. However, using deep learning method, most existing works with good performance has a large number of parameters. In order to further improve recognition speed and ensure the accuracy, we propose a lightweight neural network architecture to recognize sketch object. Specifically, we apply depthwise separable convolution into the network to reduce parameters and adjust the network effectively for the sparsity of sketch. Outperforming the state-of-the-art approaches, we achieves 85.8% and 84.1% on TU-Berlin and QuickDraw benchmarks respectively. Furthermore, the number of parameters is reduced to a large extent, which are 5% and 20% of the amount of Sketch-A-Net and MobileNets. We also develop a sketch recognition application on mobile phones to demonstrate the proposed scheme.

show abstract

Sketch recognition using transfer learning

Cited by 21 publications

References 36 publications

Entropy information‐based heterogeneous deep selective fused features using deep convolutional neural network for sketch recognition

Entropy information‐based heterogeneous deep selective fused features using deep convolutional neural network for sketch recognition

SKETRACK: Stroke-Based Recognition of Online Hand-Drawn Sketches of Arrow-Connected Diagrams and Digital Logic Circuit Diagrams

LW-Sketch-Net on Mobile Phones

Contact Info

Product

Resources

About