Removing gloss using Deep Neural Network for 3D Reconstruction

2019 ◽  
Vol 2019 (1) ◽  
pp. 143-148
Author(s):  
Futa Matsushita ◽  
Ryo Takahasshi ◽  
Mari Tsunomura ◽  
Norimichi Tsumura
Keyword(s):  
Neural Network ◽  
3D Reconstruction ◽  
Conventional Method ◽  
Deep Neural Network ◽  
High Accuracy ◽  
Simple Shape ◽  
3D Shape ◽  
Illumination Direction ◽  
Rgb Images ◽  
3D Shapes

3D reconstruction is used for inspection of industrial products. The demand for measuring 3D shapes is increased. There are many methods for 3D reconstruction using RGB images. However, it is difficult to reconstruct 3D shape using RGB images with gloss. In this paper, we use the deep neural network to remove the gloss from the image group captured by the RGB camera, and reconstruct the 3D shape with high accuracy than conventional method. In order to do the evaluation experiment, we use CG of simple shape and create images which changed geometry such as illumination direction. We removed gloss on these images and corrected defect parts after gloss removal for accurately estimating 3D shape. Finally, we compared 3D estimation using proposed method and conventional method by photo metric stereo. As a result, we show that the proposed method can estimate 3D shape more accurately than the conventional method.

scholarly journals Reconstructing 3D Model from Single-View Sketch with Deep Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Fei Wang ◽  
Yu Yang ◽  
Baoquan Zhao ◽  
Dazhi Jiang ◽  
Siwei Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Shape Reconstruction ◽  
Reconstruction Method ◽  
Single View ◽  
3D Shape ◽  
Proposed Model ◽  
Reconstruction Performance ◽  
3D Shape Reconstruction ◽  
3D Shapes

In this paper, we introduce a novel 3D shape reconstruction method from a single-view sketch image based on a deep neural network. The proposed pipeline is mainly composed of three modules. The first module is sketch component segmentation based on multimodal DNN fusion and is used to segment a given sketch into a series of basic units and build a transformation template by the knots between them. The second module is a nonlinear transformation network for multifarious sketch generation with the obtained transformation template. It creates the transformation representation of a sketch by extracting the shape features of an input sketch and transformation template samples. The third module is deep 3D shape reconstruction using multifarious sketches, which takes the obtained sketches as input to reconstruct 3D shapes with a generative model. It fuses and optimizes features of multiple views and thus is more likely to generate high-quality 3D shapes. To evaluate the effectiveness of the proposed method, we conduct extensive experiments on a public 3D reconstruction dataset. The results demonstrate that our model can achieve better reconstruction performance than peer methods. Specifically, compared to the state-of-the-art method, the proposed model achieves a performance gain in terms of the five evaluation metrics by an average of 25.5% on the man-made model dataset and 23.4% on the character object dataset using synthetic sketches and by an average of 31.8% and 29.5% on the two datasets, respectively, using human drawing sketches.

scholarly journals MeshNet: Mesh Neural Network for 3D Shape Representation

2019 ◽  
Vol 33 ◽  
pp. 8279-8286 ◽  
Author(s):  
Yutong Feng ◽  
Yifan Feng ◽  
Haoxuan You ◽  
Xibin Zhao ◽  
Yue Gao
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Point Cloud ◽  
State Of The Art ◽  
Shape Representation ◽  
Shape Classification ◽  
Retrieval Performance ◽  
3D Shape ◽  
General Architecture ◽  
3D Shapes

Mesh is an important and powerful type of data for 3D shapes and widely studied in the field of computer vision and computer graphics. Regarding the task of 3D shape representation, there have been extensive research efforts concentrating on how to represent 3D shapes well using volumetric grid, multi-view and point cloud. However, there is little effort on using mesh data in recent years, due to the complexity and irregularity of mesh data. In this paper, we propose a mesh neural network, named MeshNet, to learn 3D shape representation from mesh data. In this method, face-unit and feature splitting are introduced, and a general architecture with available and effective blocks are proposed. In this way, MeshNet is able to solve the complexity and irregularity problem of mesh and conduct 3D shape representation well. We have applied the proposed MeshNet method in the applications of 3D shape classification and retrieval. Experimental results and comparisons with the state-of-the-art methods demonstrate that the proposed MeshNet can achieve satisfying 3D shape classification and retrieval performance, which indicates the effectiveness of the proposed method on 3D shape representation.

CTL-DNNet: Effective Circular Traffic Light Recognition with a Deep Neural Network

2017 ◽  
Vol 31 (11) ◽  
pp. 1750037 ◽  
Author(s):  
Di Wang ◽  
Hong Bao ◽  
Feifei Zhang
Keyword(s):  
Neural Network ◽  
Autonomous Vehicles ◽  
Deep Neural Network ◽  
Road Traffic ◽  
High Accuracy ◽  
Activation Functions ◽  
Traffic Light ◽  
Traffic Lights ◽  
Learning Network ◽  
Deep Learning Network

This paper proposed an algorithm for a deep learning network for identifying circular traffic lights (CTL-DNNet). The sample labeling process uses translation to increase the number of positive samples, and the similarity is calculated to reduce the number of negative samples, thereby reducing overfitting. We use a dataset of approximately 370[Formula: see text]000 samples, with approximately 20[Formula: see text]000 positive samples and approximately 350[Formula: see text]000 negative samples. The datasets are generated from images taken at the Beijing Garden Expo. To obtain a very robust method for the detection of traffic lights, we use different layers, different cost functions and different activation functions of the depth neural network for training and comparison. Our algorithm has evaluated autonomous vehicles in varying illumination and gets the result with high accuracy and robustness. The experimental results show that CTL-DNNet is effective at recognizing road traffic lights in the Beijing Garden Expo area.

scholarly journals MajraDoc an Image based Disease Detection App for Agricultural Plants using Deep Learning Techniques

2021 ◽  
Author(s):  
Sara Saleh Alfozan ◽  
Mohamad Mahdi Hassan
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Food Safety ◽  
Early Detection ◽  
Deep Neural Network ◽  
High Accuracy ◽  
Vital Role ◽  
Mobile App ◽  
Learning Techniques ◽  
Agricultural Plants

Infection of agricultural plants is a serious threat to food safety. It can severely damage plants' yielding capacity. Farmers are the primary victims of this threat. Due to the advancement of AI, image-based intelligent apps can play a vital role in mitigating this threat by quick and early detection of plants infections. In this paper, we present a mobile app in this regard. We have developed MajraDoc to detect some common diseases in local agricultural plants. We have created a dataset of 10886 images for ten classes of plants diseases to train the deep neural network. The VGG-19 network model was modified and trained using transfer learning techniques. The model achieved high accuracy, and the application performed well in predicting all ten classes of infections.

scholarly journals Two particle picking procedures for filamentous proteins: SPHIRE-crYOLO filament mode and SPHIRE-STRIPER

2020 ◽  
Author(s):  
Thorsten Wagner ◽  
Luca Lusnig ◽  
Sabrina Pospich ◽  
Markus Stabrin ◽  
Fabian Schönfeld ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Molecular Complexes ◽  
High Accuracy ◽  
The Other ◽  
Line Detection ◽  
Data Sets ◽  
Detection Approach ◽  
Selection Of

AbstractStructure determination of filamentous molecular complexes involves the selection of filaments from cryo-EM micrographs. The automatic selection of helical specimens is particularly difficult and thus many challenging samples with issues such as contamination or aggregation are still manually picked. Here we present two approaches for selecting filamentous complexes: one uses a trained deep neural network to identify the filaments and is integrated in SPHIRE-crYOLO, the other one, called SPHIRE-STRIPER, is based on a classical line detection approach. The advantage of the crYOLO based procedure is that it accurately performs on very challenging data sets and selects filaments with high accuracy. Although STRIPER is less precise, the user benefits from less intervention, since in contrast to crYOLO, STRIPER does not require training. We evaluate the performance of both procedures on tobacco mosaic virus and filamentous F-actin data sets to demonstrate the robustness of each method.

scholarly journals Comprehensive Pineapple Segmentation Techniques with Intelligent Convolutional Neural Network

2018 ◽  
Vol 10 (3) ◽  
pp. 1098
Author(s):  
Muhammad Azmi Ahmed Nawawi ◽  
Fatimah Sham Ismail ◽  
Hazlina Selamat
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Decision Maker ◽  
Conventional Method ◽  
Template Matching ◽  
High Accuracy ◽  
Matching Method ◽  
Pineapple Fruit ◽  
Segmentation Image ◽  
Normalized Difference Index

<span>This paper proposes an intelligent segmentation technique for pineapple fruit using Convolutional Neural Network (CNN). Cascade Object Detector (COD) method is used to detect the position of the pineapple from the captured image by returning the bounding box around the detecting pineapple. Image background such as ground, sky and other unwanted objects have been removed using Hue value, Adaptive Red and Blue Chromatic Map (ARB) and Normalized Difference Index (NDI) methods. However, the ARB and NDI methods are still producing misclassified error and the edge is not really smooth. In this case Template Matching Method (TMM) has been implemented for image enhancement process. Finally, an intelligent CNN is developed as a decision maker to select the best segmentation image ouput from ARB and NDI. The results obtained show that the proposed intelligent method has successfully verified the fruit from the background with high accuracy as compared to the conventional method.</span>

scholarly journals DISIR: DEEP IMAGE SEGMENTATION WITH INTERACTIVE REFINEMENT

2020 ◽  
Vol V-2-2020 ◽  
pp. 877-884
Author(s):  
G. Lenczner ◽  
B. Le Saux ◽  
N. Luminari ◽  
A. Chan-Hon-Tong ◽  
G. Le Besnerais
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Deep Neural Network ◽  
Training Data ◽  
Aerial Images ◽  
Interactive Approach ◽  
Rgb Images ◽  
Deep Image ◽  
Class Segmentation ◽  
The Impact

Abstract. This paper presents an interactive approach for multi-class segmentation of aerial images. Precisely, it is based on a deep neural network which exploits both RGB images and annotations. Starting from an initial output based on the image only, our network then interactively refines this segmentation map using a concatenation of the image and user annotations. Importantly, user annotations modify the inputs of the network – not its weights – enabling a fast and smooth process. Through experiments on two public aerial datasets, we show that user annotations are extremely rewarding: each click corrects roughly 5000 pixels. We analyze the impact of different aspects of our framework such as the representation of the annotations, the volume of training data or the network architecture. Code is available at this address.

An Estimation Method of Human Impression Factors for Objects from their 3D Shapes Using a Deep Neural Network

2018 ◽  
Vol 2018 (13) ◽  
pp. 194-1-194-6
Author(s):  
Koichi Taguchi ◽  
Manabu Hashimoto ◽  
Kensuke Tobitani ◽  
Noriko Nagata
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Estimation Method ◽  
3D Shapes
Sign in / Sign up

Export Citation Format

Share Document