Evaluating Deep Convolutional Neural Networks for Material Classification

03/12/2017
by   Grigorios Kalliatakis, et al.
0

Determining the material category of a surface from an image is a demanding task in perception that is drawing increasing attention. Following the recent remarkable results achieved for image classification and object detection utilising Convolutional Neural Networks (CNNs), we empirically study material classification of everyday objects employing these techniques. More specifically, we conduct a rigorous evaluation of how state-of-the art CNN architectures compare on a common ground over widely used material databases. Experimental results on three challenging material databases show that the best performing CNN architectures can achieve up to 94.99% mean average precision when classifying materials.

READ FULL TEXT
research
11/09/2017

Material Classification in the Wild: Do Synthesized Training Data Generalise Better than Real-World Training Data?

We question the dominant role of real-world training images in the field...
research
03/12/2017

Detection of Human Rights Violations in Images: Can Convolutional Neural Networks help?

After setting the performance benchmarks for image, video, speech and au...
research
10/17/2017

Material Classification using Neural Networks

The recognition and classification of the diversity of materials that ex...
research
12/01/2014

Material Recognition in the Wild with the Materials in Context Database

Recognizing materials in real-world images is a challenging task. Real-w...
research
03/05/2019

Distinguishing mirror from glass: A 'big data' approach to material perception

Visually identifying materials is crucial for many tasks, yet material p...
research
06/07/2018

Model-based active learning to detect isometric deformable objects in the wild with deep architectures

In the recent past, algorithms based on Convolutional Neural Networks (C...
research
07/05/2020

Deep Learning based Dimple Detection for Quantitative Fractography

In this work, we try to address the challenging problem of dimple detect...

Please sign up or login with your details

Forgot password? Click here to reset