Brazil

Due to the positive relationship between the presence of students in classes and their performance, student attendance assessment is considered essential within the classroom environment, even as a tiring and time-consuming task. We proposed a solution for student attendance control using face recognition with deep one-shot learning and evaluated our approach in different conditions and image capturing devices to confirm that such a pipeline may work in a real-world setting. For better results regarding the high number of false negatives that often occur in uncontrolled environments, we also proposed a face detection stage using HOG and a CNN with Max-Margin Object Detection based features. We achieved accuracy and F1 scores of 97% and 98.4% with an iPhone 7 camera, 91.9% and 94.8% with a Moto G camera, and 51.2% and 61.1% with a WebCam respectively. These experiments reinforce the effectiveness and availability of this approach to the student attendance assessment problem since the recognition pipeline can be either made available for embedded processing with limited computational resources (smartphones), or offered as &quot;Software as a Service&quot; tool.

IWSSIP 2020

Automatic Attendance Management System based on Deep One-Shot Learning

attendance system

deep learning applications

face recognition

one shot learning

image processing

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


ICPR 2020

Due to the positive relationship between the presence of students in classes and their performance, student attendance assessment is considered essential within the classroom environment, even as a tiring and time-consuming task. We proposed a solution for student attendance control using face recognition with deep one-shot learning and evaluated our approach in different conditions and image capturing devices to confirm that such a pipeline may work in a real-world setting. For better results regarding the high number of false negatives that often occur in uncontrolled environments, we also proposed a face detection stage using HOG and a CNN with Max-Margin Object Detection based features. We achieved accuracy and F1 scores of 97% and 98.4% with an iPhone 7 camera, 91.9% and 94.8% with a Moto G camera, and 51.2% and 61.1% with a WebCam respectively. These experiments reinforce the effectiveness and availability of this approach to the student attendance assessment problem since the recognition pipeline can be either made available for embedded processing with limited computational resources (smartphones), or offered as "Software as a Service" tool.

technical paper

The 27th International Conference on Systems, Signals and Image Processing.

Face recognition has been one of the most relevant and explored Biometrics fields. In real-world applications, face recognition methods usually must deal with scenarios where not all probe individuals were seen during training phase (open-set scenarios). Therefore, open-set face recognition is a subject of increasing interest as it deals with identifying individuals in a space where not all faces are known in advance. This is useful in several applications, such as access authentication, on which only a few individuals that have been previously enrolled in a gallery are allowed. The present work introduces a novel approach towards open-set face recognition focusing on small galleries and in enrollment detection, not identity retrieval. A Siamese Network architecture is proposed to learn a model to detect if a face probe is enrolled in the gallery based on a verification-like approach. Promising results were achieved for small galleries, outperforming state-of-the-art methods like HFCN and HPLS, on experiments carried out on Pubfig83, FRGCv1 and LFW datasets. In addition, a new evaluation protocol is introduced for experiments in small galleries.

Open-set Face Recognition for Small Galleries Using Siamese Networks

Automatic speaker recognition is drastically
degraded in presence of noise. This paper focuses on the application of the cubic law and histogram mapping for the textindependent speaker recognition task. Our aim of this study is the application of these two methods in the feature extraction stage of the Power-Normalized Cepstral Coefficients (PNCC) and the conventional Mel Frequency Cepstral Coefficients (MFCC) techniques. Recognition results show that the cubic law combined with the histogram mapping improve the recognition rates.

Cubic Law and MAP Compensation Techniques for Robust Text-Independent Speaker Identification

Dysplasia is a common oral premalignant lesion type that can be classified as mild, moderate and severe. The diagnosis of different types of dysplasia is made by a pathologist through complex and time consuming histological image analysis. The use of computer-aided diagnosis can be applied as a tool to aid and enhance the pathologists decisions. Recently, deep learning based methods are earning more and more attention and have been successfully applied to nuclei segmentation problems in several scenarios. In this paper, we present a method for automated nuclei segmentation on dysplastic oral tissues histological images using convolutional neural networks. We also evaluated the impact of color normalization techniques applied to the automated nuclei segmentation task on hematoxylin-eosin stained histological images. The proposed method achieves the best results overall when validated against other segmentation methods using a dataset composed of mice tongue histopathological images.

Automated Nuclei Segmentation on Dysplastic Oral Tissues Using CNN

This work presents the Link-Quality Aware and Thermal Aware On-Demand Routing (LATOR) protocol, a proposal for routing in Wireless Body Area Networks (WBAN). LATOR improves Packet Delivery Rate (PDR) in intra-WBAN communication with node overheating prevention. This protocol avoids overheating considering only each node’s temperature without exchanging temperature information between neighboring nodes, which allows a decrease in control traffic. LATOR also considers route selection based on Link Quality Information (LQI). Initially the Received Signal Strength Indicator (RSSI) was considered as LQI. The proposal was implemented and evaluated using the Castalia framework over the OMNET++ simulator. Experimental results show that LATOR allows better PDR performance, especially when the direct communication presents low quality and there is an alternative path with better quality. At the same time, overheating in the network is avoided and PDR adequate performance is maintained. Although LATOR increases end-to-end latency, it can be considered a viable alternative for WBANs applications.

LATOR: Link-Quality Aware and Thermal Aware On-Demand Routing Protocol for WBAN

This presentation is composed of two main contributions. The first one concerns the segmentation of plantar foot thermal images. It consists of using the deep learning method U-Net to segment the thermal images. U-Net is trained by combining the two types of images (thermal and color) given by the thermal camera FLIR ONE Pro. Results show that this multimodal approach performs better than the one using only
thermal images, especially for difficult cases. The second part is devoted to a transversal clinical study conducted within the Hospital National Dos de Mayo in Lima, Peru. 122 type II diabetic patients without ulcer were recruited. These individuals were classified into three risk groups of developing a foot ulcer. This
classification is based on a medical examination: a low-risk group (R0), a medium-risk group (R1) and finally a high-risk group (R2).The results demonstrate that thermal camera temperature assessment could help in the diagnosis of diabetic foot.

Segmentation of Plantar Foot Thermal Images: Application to Diabetic Foot Diagnosis

Query performance prediction (QPP) is the namegiven to approaches that aim at predicting, usually post-query, thequality of results generated by an IR system. Yet, the indirect waythat standard QPP approaches estimate performance is opaque,has little relation to the way users evaluate queries, and islimited in application. An alternative, more challenging way tolook at the QPP problem is as arelevance predictionproblem.Instead of resulting in a quality estimate, relevance predictionaims at predicting the relevance of the top-k results in a rank.When accurate, those predictions can be directly employed as amechanism to improve the initial rank. In this work, we explorea learning framework based on sequence labeling combined withcontextual features for relevance prediction. Sequence labelingis a common approach to deal with sequential data, learningfrom the sequence to generate a sequence of predicted labels.The context within a rank, that is, the neighborhood of rankedobjects, has been successfully explored within rank-aggregationand re-ranking scenarios, and here we extend the idea to devisean effective relevance prediction feature. We show that thecombination of both can beat the baseline relevance predictionapproach, performing effective prediction, that is accurate for upto k = 30 positions.

Contextual Features and Sequence Labeling Techniques for Relevance Prediction in Retrieval

Personalized music systems usually rely on manual song annotations (tags) as a mechanism for querying and navigating large music collections. However, the manual annotation is a hard task given the large amount of music available nowadays. Automatic song annotation based on content analysis is a potential solution to this problem and has recently been gaining attention. In this work, we propose to extend the Stacking prediction framework to use Convolutional Neural Networks (CNNs) in order to improve music tag annotation task. In general, the Stacked prediction consists of a technique in which the output of the first stage of learning is used as input in the second stage. In our work we have tried two proposals of extension. The first one consists of using the weights learned by the CNN in the first stage of training as input in the second stage. In the second proposal, we use the autoencoder technique with the weights learned by CNN in the first stage to generate images 50% smaller than the ones used as input of the first stage. The weights and the images obtained in the first stage are used as input in the second stage. We evaluated our proposals with five different CNN models in three datasets well-known in the literature (FMA, MillionSong, and MagnaTagATune), obtaining interesting results.

Improving Musical Tag Annotation with Stacking and Convolutional Neural Networks

The number of Distributed Denial of Service (DDoS) attacks using IoT devices has increased in recent years. Reasons for this growth include the security limitations of IoT devices, the number of devices, and their geographic distribution. Developing mechanisms to detect and mitigate DDoS attacks in this scenario is a current challenge in the area of network security. In the literature review, it is seen that recent academic works still tries to find the best way to combat this type of threat, with proposals that need to be tested against modern datasets that contain a diversity of modern denial of service attacks. This work proposes a detection module for an IoT controller that uses Machine Learning techniques to classify network traffic. The system was designed in the Software-Defined Networks (SDN) context and evaluated on an emulated platform using three actual and well-know datasets present in the literature. The results, at a sampling rate of 20% of network traffic, show a high precision, above 93%, a low false alarm rate, and detection rate of attacks above 96%, using a low profile emulated device.

Smart Detection-IoT: A DDoS Sensor System for Internet of Things

Ultrasonic signals are widely used to detect defectsand characterize materials. In this field, the Total Focusing Method (TFM) imaging approach is commonly applied to post-process the ultrasonic data acquired by the Full Matrix Capture (FMC) of an array of ultrasonic transducers. Although the traditional FMC-TFM technique is considered as a reference standard, the energy transmitted in the material is limited by the use of a single transmitting element of the array and hence may provide a poor signal-to-noise ratio of the reconstructed image. To overcome this limitation and improve the image quality of highly noisy materials, this paper combines two noise-reduction methods, namely a modified Spatially Averaged Sub-ApertureCorrelation Imaging and virtual sources. In the former, we further propose a modification in order to avoid the manual fine-tuning of a parameter presented in the original approach. The second consists of using several transmitting elements to increase theenergy transmitted in the medium. Results showed that this combination was able to increase in 39dB the signal-to-noise ratio. This result is 4.2dB above the sum of individual gains of each technique which indicates a synergistic effect on increasing the image quality. Moreover, the use of virtual sources was capable of improving the reconstructed image where initially it is not possible to distinguish the noise from the desired signal. The application of the correlation approach in this scenario increased the quality of the reconstructed image significantly. The proposed combination was validated in a finite element model of a steel block with side-drilled holes used to mimic internal flaws in the material. Several noise levels were added to the numerically simulated signals in order to evaluate the performance of the proposed approach.

Improvement of Ultrasonic Image by a Combination of Correlation-Based Image Processing and Virtual Sources Applied to Non-Destructive Evaluation

In this contribution a design of a full polarimetric multi-channel Ground Penetrating Radar (GPR) with optimized antenna switching is presented. Firstly, a single-polarized system was used to obtain multiple measurements of a static scene with different antenna orientation and providing a full polarimetric dataset. Laboratory experiments have been performed on metal test landmines and where promising results have been obtained. The single-polarized radar system was modified to a multichannel system with focus on decreasing the scanning time. The selected frequency range covers the band of 550 MHz to 2.7 GHz, which corresponds in soil to a range resolution of approximately 7 cm. There was no need to use a Power Amplifier (PA) at the transmitter stage, since a highly sensitive receiver is implemented. This greatly decrease the power consumption and makes the device suitable for battery powered platforms. Physical contact between the ground and antennas was avoided with using the air-launched measurement technique, where additionally the level of safety is higher.

Premium content

Automatic Attendance Management System based on Deep One-Shot Learning

Downloads

Next from IWSSIP 2020

Open-set Face Recognition for Small Galleries Using Siamese Networks

Similar lecture

Detection of Makeup Presentation Attacks based on Deep Face Representations

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES