2d Image Features Detector and Descriptor Selection Expert System

Merino, Ibon; Azpiazu, Jon; Remazeilles, Anthony; Sierra, Basilio

doi:10.5121/csit.2019.91206

Cited by 4 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For evaluating our face recognition approaches, we use multiple feature extraction methods and classification techniques. Regarding feature extraction, we use hand-crafted features by exploiting the SURF [60] and HOG [28] descriptors. On the other hand, learned features [61] are extracted from the final layers of the pre-trained Inception-v3 deep architecture model [29].…”

Section: Feature Extraction and Classificationmentioning

confidence: 99%

Comparative Study Based on De-Occlusion and Reconstruction of Face Images in Degraded Conditions

Ouannes¹,

Khalifa²,

Amara³

2021

View full text Add to dashboard Cite

In the recent years, the face recognition task has attracted the attention of researchers due to its efficiency in several domains such as surveillance and access control. Unfortunately, there are multiple challenges that decrease the performance of face recognition. Partial occlusion is the most challenging one since it often causes a great lack of information. The main purpose of this paper is to prove that facial reconstruction improves the results of facial recognition compared to de-occlusion and full-face recognition in the presence of occlusion. Our objective is to achieve occluded-face recognition, de-occluded-face recognition, and reconstructed-face recognition. Regarding face reconstruction, we introduce two different methods based on Laplacian pyramid blending and CycleGANs. In order to validate our work, we perform two different feature extraction techniques: hand-crafted features and learned features exploiting the final layers of a pre-trained deep architecture model. The experimental results on the EURECOM Kinect Face Dataset (EKFD) and the IST-EURECOM Light Field Face Database (IST-EURECOM LFFD) show that the proposed face reconstruction approach, compared with the face de-occlusion and occluded-face recognition ones, clearly improves the face recognition task. Our method boosts the classification performance in comparison with the state-of-the-art methods, achieving 94.66% on EKFD and 72.35% on IST-EURECOM LFFD.

show abstract

Section: Feature Extraction and Classificationmentioning

confidence: 99%

Comparative Study Based on De-Occlusion and Reconstruction of Face Images in Degraded Conditions

Ouannes¹,

Khalifa²,

Amara³

2021

View full text Add to dashboard Cite

show abstract

“…Despite a difference of such tasks, they exploit almost the same tool set. Examples of such tools may be 2D feature detection [1], contour processing [2], edge detections, threshing, etc. There are limited number of such fundamental processing operations, but all of them are so flexible, so it could satisfy almost every case or task.…”

Section: Introductionmentioning

confidence: 99%

Exploit computer vision inpainting approach to boost deep learning models

Baranov¹,

Shcherbyna²,

Khodych³

2022

Vìsn. Nac. unìv. "Lʹvìv. polìteh.", Ser. Ìnf. sist. merežì

View full text Add to dashboard Cite

In today’s world, the amount of available information grows exponentially every day. Most of this data is visual data. Correspondingly, the demand for the algorithm of image rent is growing. Traditionally, the first approaches to computer vision problems were classical algorithms without the use of machine learning. Such approaches are limited by many factors. First of all, the conditions imposed on the input images are applied – the shooting angle, lighting, position of objects on the scene, etc. Other classical algorithms cannot meet the needs of modern computer vision problems. Neural network approaches and deep learning models have largely replaced classical programming algorithms. The greatest advantage of deep neural networks in computer vision tasks is not only the possibility of automatically building data processing algorithms that cannot be built in any other way, but also the comprehensiveness of such an approach – actual deep neural networks provide all stages of image processing from start to finish. But. This approach is not always optimal. Training models require a large amount of annotated data to avoid the effect of overfitting such models. In many settings, the conditions have a significant degree of variability, but are limited. In such cases, the combination of both approaches of computer vision is fruitful – pre-processing of the image is performed by classical algorithms, and prediction (classification, object search, etc.) is performed by a neural network. This article noted an example of the use of damaged images in the classification of tasks (in the extreme cases, the percentage of damage reached 60 % of the image area). We have shown in practice that the use of classic approaches for restoration of damaged areas of the image (inpainting) made it possible to increase the final accuracy of the model by up to 10 % compared to the base model trained under identical conditions on the original data.

show abstract