Initialization of convolutional neural networks by Gabor filters

Özbulak, Gökhan; Ekenel, Hazım Kemal

doi:10.1109/siu.2018.8404757

Cited by 12 publications

(10 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[48] 96.60 FLBP [49] 98.45 dominant LBP [50] 95.66 quantised fuzzy LBP [51] 98.87 local ternary pattern (LTP) [52] 97. 39 LGFV/LN/LLE…”

Section: Resultsmentioning

confidence: 99%

Locally lateral manifolds of normalised Gabor features for face recognition

Zaman

2020

IET Computer Vision

View full text Add to dashboard Cite

Due to inherent characteristics of multiscale and orientation, normalised Gabor features have been successfully used in face recognition. Various previous works have showcased the strength and feasibility of this approach, especially on its robustness against local variations. However, the projected features are numerous and substantial in dimension, which is largely due to the convolution of multiscale and orientation of wavelets. Such features, when used in practical face recognition, would require relatively lengthy classification process, particularly when it involves computationally extensive local classifier or experts, such as ensembles of local cosine similarity (ELCS) classifier. The authors address this issue by simultaneously reducing the size of Gabor features laterally and locally using a manifold learning method called locally linear embedding (LLE). This method is thus denoted as locally lateral normalised local Gabor feature vector with LLE (LGFV/LN/LLE). Results on several publicly available face datasets reveal the superiority of the authors’ approach in terms of improvements in feature compression of LGFV features by up to a reduction of 95% of total dimensionality while increasing the average classification accuracy by 26%. Altogether, the authors show that their LGFV/LN/LLE augmented by ELCS classifiers delivers equivalent result when compared against the state‐of‐the‐art.

show abstract

“…[48] 96.60 FLBP [49] 98.45 dominant LBP [50] 95.66 quantised fuzzy LBP [51] 98.87 local ternary pattern (LTP) [52] 97. 39 LGFV/LN/LLE…”

Section: Resultsmentioning

confidence: 99%

Locally lateral manifolds of normalised Gabor features for face recognition

Zaman

2020

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…Typically, in AI models, the earlier layers of the models are focused on identifying simple features such as edges, straight lines, and curves. As the layers progress, they then start to identify objects with increasing complexity: from simple shapes such as circles, through to more abstract objects such as faces [ 54 ]. The activations from the final layers are then used to make the final decision on what the original image is most likely to be based on the model architecture.…”

Section: Discussionmentioning

confidence: 99%

Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models

et al. 2022

View full text Add to dashboard Cite

While color fundus photos are used in routine clinical practice to diagnose ophthalmic conditions, evidence suggests that ocular imaging contains valuable information regarding the systemic health features of patients. These features can be identified through computer vision techniques including deep learning (DL) artificial intelligence (AI) models. We aim to construct a DL model that can predict systemic features from fundus images and to determine the optimal method of model construction for this task. Data were collected from a cohort of patients undergoing diabetic retinopathy screening between March 2020 and March 2021. Two models were created for each of 12 systemic health features based on the DenseNet201 architecture: one utilizing transfer learning with images from ImageNet and another from 35,126 fundus images. Here, 1277 fundus images were used to train the AI models. Area under the receiver operating characteristics curve (AUROC) scores were used to compare the model performance. Models utilizing the ImageNet transfer learning data were superior to those using retinal images for transfer learning (mean AUROC 0.78 vs. 0.65, p-value < 0.001). Models using ImageNet pretraining were able to predict systemic features including ethnicity (AUROC 0.93), age > 70 (AUROC 0.90), gender (AUROC 0.85), ACE inhibitor (AUROC 0.82), and ARB medication use (AUROC 0.78). We conclude that fundus images contain valuable information about the systemic characteristics of a patient. To optimize DL model performance, we recommend that even domain specific models consider using transfer learning from more generalized image sets to improve accuracy.

show abstract

“…The steerable Gabor filters have the property of extracting low-level features from images thus utilizing them eliminates the need for transfer learning. Moreover, experiments conducted in [29] emphasize that the use of Gabor filters helps in fast convergence.…”

Section: Highlightsmentioning

confidence: 99%

“…In our research work, Gabor filters are integrated, and two new CNN models are developed on a cloud environment for visual sentiment recognition. The Gabor integration with CNN is due to the main reasons for a decrease in computation energy [26] [28], time [28] [29], and improved performance [27] [29]. We also developed a modified 3D information diagram method to design Gabor filters that are suitable for integration with CNN.…”

Section: Literature Surveymentioning

confidence: 99%

Gabor CNN Based Intelligent System for Visual Sentiment Analysis of Social Media Data on Cloud Environment

2022

View full text Add to dashboard Cite

Social media contains a plethora of information in the form of text, images, videos, and other data. Users across the globe are increasingly sharing their data on various social media platforms. Sentiment analysis of data, such as text, images, and videos are widely used to understand the feelings of users. In recent years, the convolutional neural network (CNN) has been extensively applied for various applications. The cloud computing environment is a popular service due to its reliability, availability, and easy software integration. However, CNN models are deep neural networks that have a high computational cost. There is a need for CNN models which utilize lesser computational resources especially when these models are deployed in a cloud environment due to the remote physicality of servers, resource optimization, and infrastructure cost reduction. In this research, Gabor filters are integrated with CNN models to improve image sentiment analysis in a cloud environment, with advantages such as the reduction in computation energy and time, the elimination of the need for pre-trained models, and a perceived accuracy improvement. Two variants of Gabor-CNN (G-CNN) models with a different number of pooling and normalization layers are developed. The proposed G-CNN is trained and tested using five standard databases as SentiBank, Twitter, MVSO, MultiView_I, and MultiView_II. Maximum classification accuracies of 91.71%, 92.52%, 97.39%, 90.88%, and 91.31% are obtained on SentiBank, Twitter, MVSO, MultiView_I, and MultiView_II databases respectively using the developed models. The proposed G-CNN model has provided an accuracy of 92.76% on average.

show abstract

Initialization of convolutional neural networks by Gabor filters

Cited by 12 publications

References 5 publications

Locally lateral manifolds of normalised Gabor features for face recognition

Locally lateral manifolds of normalised Gabor features for face recognition

Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models

Gabor CNN Based Intelligent System for Visual Sentiment Analysis of Social Media Data on Cloud Environment

Contact Info

Product

Resources

About