Publications related to Low complexity image recognition algorithm for handheld applications

Related publications (30)

Development and clinical validation of computational imaging biomarkers for neurodegenerative diseases

Neurodegenerative and neuroinflammatory disorders often involve complex pathophysiological mechanisms that are â to this date â only partially understood. A more comprehensive understanding of those microstructural processes and their characterization ...

EPFL2024

Scale-Aware Test-Time Click Adaptation for Pulmonary Nodule and Mass Segmentation

Li Zhang, Jiancheng Yang

Pulmonary nodules and masses are crucial imaging features in lung cancer screening that require careful management in clinical diagnosis. Despite the success of deep learning-based medical image segmentation, the robust performance on various sizes of lesi ...

Springer International Publishing Ag2023

Cross-resolution Face Recognition via Identity-Preserving Network and Knowledge Distillation

Touradj Ebrahimi, Yuhang Lu

Cross-resolution face recognition has become a challenging problem for modern deep face recognition systems. It aims at matching a low-resolution probe image with high-resolution gallery images registered in a database. Existing methods mainly leverage pri ...

2023

Knowledge-Aware Cross-Modal Text-Image Retrieval for Remote Sensing Images

Devis Tuia, Christel Marie Tartini-Chappuis, Li Mi, Siran Li

Image-based retrieval in large Earth observation archives is difficult, because one needs to navigate across thousands of candidate matches only with the proposition image as a guide. By using text as a query language, the retrieval system gains in usabili ...

2022

QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval

Shaokai Ye

We study the query-based attack against image retrieval to evaluate its robustness against adversarial examples under the black-box setting, where the adversary only has query access to the top-1 ranked unlabeled images from the database. Compared with que ...

IEEE COMPUTER SOC2021

Semantics-Aware Spatial-Temporal Binaries for Cross-Modal Video Retrieval

Jie Luo, Mengshi Qi

With the current exponential growth of video-based social networks, video retrieval using natural language is receiving ever-increasing attention. Most existing approaches tackle this task by extracting individual frame-level spatial features to represent ...

2021

Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers

Frédéric Kaplan, Maud Ehrmann, Sofia Ares Oliveira, Raphaël Barman

The massive amounts of digitized historical documents acquired over the last decades naturally lend themselves to automatic processing and exploration. Research work seeking to automatically process facsimiles and extract information thereby are multiplyin ...

2021

Learning a Unified Blind Image Quality Metric via On-Line and Off-Line Big Training Instances

Daniel Thalmann

In this work, we resolve a big challenge that most current image quality metrics (IQMs) are unavailable across different image contents, especially simultaneously coping with natural scene (NS) images or screen content (SC) images. By comparison with exist ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

Deep Feature Factorization For Content-Based Image Retrieval And Localization

Sabine Süsstrunk, Edo Collins

State of the art content-based image retrieval algorithms owe their excellent performance to the rich semantics encoded in the deep activations of a convolutional neural network. The difference between these algorithms lies mostly in how activations are co ...

IEEE2019

Texture-driven parametric snakes for semi-automatic image segmentation

Michaël Unser, Adrien Raphaël Depeursinge, Anaïs Laure Marie-Thérèse Badoual

We present a texture-driven parametric snake for semi-automatic segmentation of a single and closed structure in an image. We propose a new energy functional that combines intensity and texture information. The two types of image information are balanced u ...

ACADEMIC PRESS INC ELSEVIER SCIENCE2019

Evaluating and Interpreting Deep Convolutional Neural Networks via Non-negative Matrix Factorization

Edo Collins

With ever greater computational resources and more accessible software, deep neural networks have become ubiquitous across industry and academia. Their remarkable ability to generalize to new samples defies the conventional view, which holds that complex, ...

EPFL2019

SUBDIVIDE AND CONQUER Active Contours and Surfaces for Biomedical Image Segmentation

Anaïs Laure Marie-Thérèse Badoual

Ongoing advances in imaging techniques create new demands regarding the analysis of images in medicine and biology. Image segmentation is a key step of many image analysis pipelines and its proper execution is a particularly challenging task. This thesis i ...

EPFL2019

Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation

Jean-Marc Odobez, Olivier Canévet, Michael Villamizar

Achieving robust multi-person 2D body landmark localization and pose estimation is essential for human behavior and interaction understanding as encountered for instance in HRI settings. Accurate methods have been proposed recently, but they usually rely o ...

2020

Learning an event sequence embedding for event-based deep stereo

François Fleuret, Stepan Tulyakov

Today, a frame-based camera is the sensor of choice for machine vision applications. However, these cameras, originally developed for acquisition of static images rather than for sensing of dynamic uncontrolled visual environments, suffer from high power c ...

IEEE2019

What Face and Body Shapes Can Tell Us About Height

Pascal Fua, Helge Jochen Rhodin, Semih Günel

Recovering a person's height from a single image is important for virtual garment fitting, autonomous driving and surveillance. However, it is also very challenging without absolute scale information. Here, we examine the rarely addressed case, where camer ...

IEEE COMPUTER SOC2019

Graph-based image representation learning

Renata Khasanova

Though deep learning (DL) algorithms are very powerful for image processing tasks, they generally require a lot of data to reach their full potential. Furthermore, there is no straightforward way to impose various properties, given by the prior knowledge a ...

EPFL2019

Learning How To Recognize Faces In Heterogeneous Environments

Tiago De Freitas Pereira

Face recognition is a mature field in biometrics in which several systems have been proposed over the last three decades. Such systems are extremely reliable under controlled recording conditions and it has been deployed in the field in critical tasks, suc ...

EPFL2019

A Versatile Method for Ice Particle Habit Classification Using Airborne Imaging Probe Data

Alexis Berne, Christophe Praz

A versatile method to automatically classify ice particle habit from various airborne optical array probes is presented. The classification is achieved using a multinomial logistic regression model. For each airborne probe, the model determines the particl ...

AMER GEOPHYSICAL UNION2018

Fractal and Complexity Analysis of Crack Patterns of Masonry Walls

Katrin Beyer, Amir Rezaie

In order to develop automatic image-based methods for damage evaluation after earthquakes, crack maps need to be evaluated using computer-based algorithms. A common method to link the crack map to a damage state is to compute the fractal dimension of the c ...

2018

Method, system, and device for learned invariant feature transform for computer images

Pascal Fua, Vincent Lepetit, Kwang Moo Yi, Eduard Trulls Fortuny

A method for training a feature detector of an image processing device, including the steps of detecting features in the image to generate a score map, computing a center of mass on the score map to generate a location, extracting a patch from the image at ...

2018