scholarly journals Neuroscope: An Explainable AI Toolbox for Semantic Segmentation and Image Classification of Convolutional Neural Nets

2021 ◽  
Vol 11 (5) ◽  
pp. 2199
Author(s):  
Christian Schorr ◽  
Payman Goodarzi ◽  
Fei Chen ◽  
Tim Dahmen
Keyword(s):  
Image Classification ◽  
New Technologies ◽  
Semantic Segmentation ◽  
Autonomous Driving ◽  
Neural Nets ◽  
Widespread Acceptance ◽  
Model View Controller ◽  
Visualization Algorithms ◽  
Model View

Trust in artificial intelligence (AI) predictions is a crucial point for a widespread acceptance of new technologies, especially in sensitive areas like autonomous driving. The need for tools explaining AI for deep learning of images is thus eminent. Our proposed toolbox Neuroscope addresses this demand by offering state-of-the-art visualization algorithms for image classification and newly adapted methods for semantic segmentation of convolutional neural nets (CNNs). With its easy to use graphical user interface (GUI), it provides visualization on all layers of a CNN. Due to its open model-view-controller architecture, networks generated and trained with Keras and PyTorch are processable, with an interface allowing extension to additional frameworks. We demonstrate the explanation abilities provided by Neuroscope using the example of traffic scene analysis.

Exposed by the Mask

Public ◽  
2020 ◽  
Vol 31 (61) ◽  
pp. 6-35
Author(s):  
Felipe Steinberg
Keyword(s):  
Video Game ◽  
New Technologies ◽  
Satellite Image ◽  
Semantic Segmentation ◽  
Autonomous Driving ◽  
Departure Point ◽  
Core Technology ◽  
Artificial Intelligence Technology ◽  
Satellite Image Processing ◽  
Leisure Industry

Semantic segmentation is the process of assigning a label – vehicle, person, sidewalk, pavement etc. -- to every pixel in an image. This artificial intelligence technology was initially created for military application, Gulf War, and it is the core technology behind autonomous driving, medical imaging technologies or satellite image processing, among others. Being from Brazil, the departure point of the project is to explore my own relation to Dakar, Senegal, through the inscriptions of colonialism and post-colonialism in the leisure industry. Before visiting Dakar in the fall of 2019 for an art residency, my relationship with it was basically mediated through a game, called “Paris-Dakar 1990”, for the video-game console Atari. This game was made as a merchandise product from the Paris Dakar race. Through juxtaposition between this ‘AI’ technology and those video game ‘vignettes’ the work is a reflection of how new technologies and engineering projects promise a revolutionary new future while replicating and reinforcing old forms of racialized, gendered and class ideas about the ‘good life’ through middle class ideology.

The Concept of Model-View-Controler (MVC) as Solution Software Development

CCIT Journal ◽  
2010 ◽  
Vol 3 (3) ◽  
pp. 377-402
Author(s):  
Ermatita Ermatita ◽  
Huda Ubaya ◽  
Dwirosa Indah
Keyword(s):  
Software Development ◽  
Model View Controller ◽  
On Line ◽  
Line Test ◽  
Model View

Pengembangan perangkat lunak adalah tugas kompleks dan membutuhkan adaptasi untuk mengakomodasi kebutuhan pengguna. Untuk membuat konsep dan perubahan perangkat lunak, dalam pemeliharaan, sekarang telah dikembangkan lebih mudah dalam pengembangan perangkat lunak, pola model-view-controller, yang merupakan arsitektur yang dapat membantu memfasilitasi dalam pengembangan dan pemeliharaan perangkat luna. Hal ini, karena dalam arsitektur model tiga-lapis, yaitu: tampilan dan pengontrolan dalam pembangunan dilakukan secara independen, sehingga dapat memberikan dahan dalam pengembangan dan pemeliharaan. Selain itu, arsitektur ini juga dapat melihat hal-hal yang sederhana dan menarik bagi pengguna. Software sistem on-line test adalah perangkat lunak yang memerlukan interaksi dengan pengguna, dan pemeliharaan perangkat adaptif. Karena sistem ujian on-line memerlukan pengembangan perangkat lunak untuk mengakomodasi kebutuhan ini berkembang dengan cepat. Makalah ini untuk menganalisis Model-View-Controller dan mencoba pembangunan, untuk menerapkannya dalam pengembangan perangkat lunak sistem pengujian on-line. 

CNN-based Classification of Degraded Images

2020 ◽  
Vol 2020 (10) ◽  
pp. 28-1-28-7 ◽  
Author(s):  
Kazuki Endo ◽  
Masayuki Tanaka ◽  
Masatoshi Okutomi
Keyword(s):  
Neural Networks ◽  
Image Restoration ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Deep Convolutional Neural Networks ◽  
Alternative Approach ◽  
Degraded Image ◽  
Degraded Images ◽  
Straightforward Approach

Classification of degraded images is very important in practice because images are usually degraded by compression, noise, blurring, etc. Nevertheless, most of the research in image classification only focuses on clean images without any degradation. Some papers have already proposed deep convolutional neural networks composed of an image restoration network and a classification network to classify degraded images. This paper proposes an alternative approach in which we use a degraded image and an additional degradation parameter for classification. The proposed classification network has two inputs which are the degraded image and the degradation parameter. The estimation network of degradation parameters is also incorporated if degradation parameters of degraded images are unknown. The experimental results showed that the proposed method outperforms a straightforward approach where the classification network is trained with degraded images only.

APLIKASI PEMESANAN MAKANAN BERBASIS WEB

e-NARODROID ◽  
2015 ◽  
Vol 1 (2) ◽  
Author(s):  
Immah Inayati
Keyword(s):  
Unified Modeling Language ◽  
Object Oriented ◽  
Modeling Language ◽  
Unified Modeling ◽  
Model View Controller ◽  
Model View

Perkembangan dunia teknologi berjalan sangat cepat. Selaras dengan hal itu, kebutuhan manusia hususnya dibidang bisnis juga semakin berkembang. salah satunya adalah R.M. Lesehan Berkah Ilaahi. Rumah makan ini merupakan rumah makan yang memiliki banyak pelanggan. Dengan semakin bertambahnya jumlah pelanggan, maka [penumpukan antrian banyak terjadi. Di samping itu rumah makan ini memiliki potensi untuk dapat terus mengembangkan bisnisnya. Untuk itu dibutuhkan sebuah sistem yang mampu memfasilitasi proses pemesanan melalui online serta mampu membantu pemilik bisnis dalam melakukan promosi dan penawaran, terlebih kepada pelanggan yang daya belinya tinggi. Jurnal ini memaparkan proses pembangunan sistem pemesanan berbasis web dengan menekankan pada tahap analisa, desain, dan implementasi. Analisis kondisi lapangan dilakukan dengan cara observasi lapangan, studi literatur sistem lama, wawancara dan kuesioner pelanggan. Hasil analisa akan digambarkan menggunakan notasi UML (Unified Modeling Language) untuk selanjutnya diimplementasikan dalam sebuah aplikasi e-CRM menggunakan bahasa pemrograman PHP serta basis data PostgreSQL. Metode pengembangan yang digunakan adalah Object oriented dengan memanfaatkan Yii Framework yang merupakan framework PHP berbasis Model View Controller (MVC). Selain itu digunakan pula bootstrap framework dari sisi desain aplikasi untuk memberikan fleksibilitas aplikasi ketika diakses dengan device yang resolusinya lebih kecil seperti telephon genggam. Kata kunci : Observasi, Wawancara, Kuesioner, UML (Unified Modeling Language), Yii Framework, Object oriented, Model View Controller (MVC), bootstrap framework.

scholarly journals Weakly-Supervised Recommended Traversable Area Segmentation Using Automatically Labeled Images for Autonomous Driving in Pedestrian Environment with No Edges

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 437
Author(s):  
Yuya Onozuka ◽  
Ryosuke Matsumi ◽  
Motoki Shino
Keyword(s):  
Visual Information ◽  
Data Augmentation ◽  
Semantic Segmentation ◽  
Autonomous Driving ◽  
Weighting Method ◽  
Personal Mobility ◽  
Human Understanding ◽  
Autonomous Mobility ◽  
Weakly Supervised ◽  
Traffic Rules

Detection of traversable areas is essential to navigation of autonomous personal mobility systems in unknown pedestrian environments. However, traffic rules may recommend or require driving in specified areas, such as sidewalks, in environments where roadways and sidewalks coexist. Therefore, it is necessary for such autonomous mobility systems to estimate the areas that are mechanically traversable and recommended by traffic rules and to navigate based on this estimation. In this paper, we propose a method for weakly-supervised recommended traversable area segmentation in environments with no edges using automatically labeled images based on paths selected by humans. This approach is based on the idea that a human-selected driving path more accurately reflects both mechanical traversability and human understanding of traffic rules and visual information. In addition, we propose a data augmentation method and a loss weighting method for detecting the appropriate recommended traversable area from a single human-selected path. Evaluation of the results showed that the proposed learning methods are effective for recommended traversable area detection and found that weakly-supervised semantic segmentation using human-selected path information is useful for recommended area detection in environments with no edges.

scholarly journals An Imbalanced Image Classification Method for the Cell Cycle Phase

Information ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 249
Author(s):  
Xin Jin ◽  
Yuanwen Zou ◽  
Zhongbing Huang
Keyword(s):  
Cell Cycle ◽  
Deep Learning ◽  
Image Classification ◽  
Classification Accuracy ◽  
Data Augmentation ◽  
Cycle Phase ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Cellular Life

The cell cycle is an important process in cellular life. In recent years, some image processing methods have been developed to determine the cell cycle stages of individual cells. However, in most of these methods, cells have to be segmented, and their features need to be extracted. During feature extraction, some important information may be lost, resulting in lower classification accuracy. Thus, we used a deep learning method to retain all cell features. In order to solve the problems surrounding insufficient numbers of original images and the imbalanced distribution of original images, we used the Wasserstein generative adversarial network-gradient penalty (WGAN-GP) for data augmentation. At the same time, a residual network (ResNet) was used for image classification. ResNet is one of the most used deep learning classification networks. The classification accuracy of cell cycle images was achieved more effectively with our method, reaching 83.88%. Compared with an accuracy of 79.40% in previous experiments, our accuracy increased by 4.48%. Another dataset was used to verify the effect of our model and, compared with the accuracy from previous results, our accuracy increased by 12.52%. The results showed that our new cell cycle image classification system based on WGAN-GP and ResNet is useful for the classification of imbalanced images. Moreover, our method could potentially solve the low classification accuracy in biomedical images caused by insufficient numbers of original images and the imbalanced distribution of original images.

Sign in / Sign up

Export Citation Format

Share Document