Improving Image Classification Robustness Using Predictive Data Augmentation

Harisubramanyabalaji, S. P.; Réhman, Shafiq Ur; Nyberg, Mattias; Gustavsson, Joakim

doi:10.1007/978-3-319-99229-7_49

Cited by 4 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Presented results shows that trained model is robust on some genotypes but it does not guaranty the robustness of the model an all genotypes or other species. In order to increase the robustness of models one could either add more real data from several genotypes or use data augmentation to synthetically increase the data variability in the training database [43][44][45] based on possible priors on the expected morphological plasticity of the species.…”

Section: Discussionmentioning

confidence: 99%

Deep learning-based detection of seedling development

Samiei

Rasti

et al. 2020

Plant Methods

View full text Add to dashboard Cite

Background: Monitoring the timing of seedling emergence and early development via high-throughput phenotyping with computer vision is a challenging topic of high interest in plant science. While most studies focus on the measurements of leaf area index or detection of specific events such as emergence, little attention has been put on the identification of kinetics of events of early seedling development on a seed to seed basis. Result: Imaging systems screened the whole seedling growth process from the top view. Precise annotation of emergence out of the soil, cotyledon opening, and appearance of first leaf was conducted. This annotated data set served to train deep neural networks. Various strategies to incorporate in neural networks, the prior knowledge of the order of the developmental stages were investigated. Best results were obtained with a deep neural network followed with a long short term memory cell, which achieves more than 90% accuracy of correct detection. Conclusion: This work provides a full pipeline of image processing and machine learning to classify three stages of plant growth plus soil on the different accessions of two species of red clover and alfalfa but which could easily be extended to other crops and other stages of development.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep learning-based detection of seedling development

Samiei

Rasti

et al. 2020

Plant Methods

View full text Add to dashboard Cite

show abstract

“…Image augmentations for street scenes done so far are either limited to a few quality deficits [6] or lack realism [7]. The possible occurrence of multiple quality deficits together is considered to some extent in [8], where different augmentations are combined using the LAB color space.…”

Section: Introductionmentioning

confidence: 99%

Safe Traffic Sign Recognition through Data Augmentation for Autonomous Vehicles Software

Jöckel

Kläs

Martínez‐Fernández

2019

2019 IEEE 19th International Conference on Software Quality, Reliability and Security Companion (QRS-C)

View full text Add to dashboard Cite

Since autonomous vehicles operate in an open context, their software components, including data-driven ones, have to reliably process inputs (e.g., obtained by cameras) in order to make safe decisions. A key challenge when providing reliable data-driven components is insufficient training data, which could lead to wrong interpretation of the environment, thereby causing accidents. Aim: The goal of our research is to extend available training data of data-driven components for safe autonomous vehicles using the example of traffic sign recognition. Method: We developed an approach to create realistic image augmentations of various quality deficits and applied them on the German traffic sign recognition benchmark dataset (GTSRB). Results: The approach results in images augmented with (any combination of) seven different quality deficits affecting traffic sign recognition (rain, dirt on lens, steam on lens, darkness, motion blur, dirt on sign, backlight) and considers dependencies between combined quality deficits and influences from other contextual information. Conclusion: Our approach can be used to obtain more comprehensive datasets, especially also including samples with quality deficits that are difficult to gather. By structuring the augmentation into a set of basic components, the approach can be adapted for other application domains (e.g., person detection).

show abstract

Increasing Trust in Data-Driven Model Validation

Jöckel

Kläs

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Improving Image Classification Robustness Using Predictive Data Augmentation

Cited by 4 publications

References 12 publications

Deep learning-based detection of seedling development

Deep learning-based detection of seedling development

Safe Traffic Sign Recognition through Data Augmentation for Autonomous Vehicles Software

Increasing Trust in Data-Driven Model Validation

Contact Info

Product

Resources

About