Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

Diffeomorphic transforms for data augmentation of highly variable shape and texture objects

  • Vállez Enano, Noelia
  • Bueno García, María Gloria
  • Déniz Suárez, Óscar
  • Blanco Lanza, Saúl
[EN] Background and objective: Training a deep convolutional neural network (CNN) for automatic image classification requires a large database with images of labeled samples. However, in some applications such as biology and medicine only a few experts can correctly categorize each sample. Experts are able to identify small changes in shape and texture which go unnoticed by untrained people, as well as distinguish between objects in the same class that present drastically different shapes and textures. This means that currently available databases are too small and not suitable to train deep learning models from scratch. To deal with this problem, data augmentation techniques are commonly used to increase the dataset size. However, typical data augmentation methods introduce artifacts or apply distortions to the original image, which instead of creating new realistic samples, obtain basic spatial variations of the original ones. Methods: We propose a novel data augmentation procedure which generates new realistic samples, by combining two samples that belong to the same class. Although the idea behind the method described in this paper is to mimic the variations that diatoms experience in different stages of their life cycle, it has also been demonstrated in glomeruli and pollen identification problems. This new data augmentation procedure is based on morphing and image registration methods that perform diffeomorphic transformations. Results: The proposed technique achieves an increase in accuracy over existing techniques of 0.47%, 1.47%, and 0.23% for diatom, glomeruli and pollen problems respectively. Conclusions: For the Diatom dataset, the method is able to simulate the shape changes in different diatom life cycle stages, and thus, images generated resemble newly acquired samples with intermediate shapes. In fact, the other methods compared obtained worse results than those which were not using data augmentation. For the Glomeruli dataset, the method is able to add new samples with different shapes and degrees of sclerosis (through different textures). This is the case where our proposed DA method is more beneficial, when objects highly differ in both shape and texture. Finally, for the Pollen dataset, since there are only small variations between samples in a few classes and this dataset has other features such as noise which are likely to benefit other existing DA techniques, the method still shows an improvement of the results, SI, The authors acknowledge financial support of the Spanish Government and Junta de Comunidades de Castilla-La Mancha under projects AQUALITAS (Ref. CTM2014-51907-C2-R-MINECO), HYPERDEEP (Ref. SBPLY/19/180501/000273), and APRENDAMOS (Ref. SBPLY/17/180501/000543). They would also like to extend the acknowledgment to technicians Enrique Cepeda and Jesus Diaz for their help in running some experiments
BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

Multi-exposure microscopic image fusion-based detail enhancement algorithm

  • Singh, Harbinder
  • Cristóbal Pérez, Gabriel
  • Bueno García, María Gloria
  • Blanco Lanza, Saúl
  • Singh, Simrandeep
  • Hrisheekesha, Periapattana Nagaraj
  • Mittal, Nitin
[EN] Traditional microscope imaging techniques are unable to retrieve the complete dynamic range of a diatom species with complex silica-based cell walls and multi-scale patterns. In order to extract details from the diatom, multi-exposure images are captured at variable exposure settings using microscopy techniques. A recent innovation shows that image fusion overcomes the limitations of standard digital cameras to capture details from high dynamic range scene or specimen photographed using microscopy imaging techniques. In this paper, we present a cell-region sensitive exposure fusion (CS-EF) approach to produce well-exposed fused images that can be presented directly on conventional display devices. The ambition is to preserve details in poorly and brightly illuminated regions of 3-D transparent diatom shells. The aforesaid objective is achieved by taking into account local information measures, which select well-exposed regions across input exposures. In addition, a modified histogram equalization is introduced to improve uniformity of input multi-exposure image prior to fusion. Quantitative and qualitative assessment of proposed fusion results reveal better performance than several state-of-the-art algorithms that substantiate the method’s validity, SI, This work was supported in part by the Spanish Government, Spain under the AQUALITAS-retos project (Ref.CTM2014-51907-C2-2-R-MINECO) and by Junta de Comunidades de Castilla-La Mancha, Spain under project HIPERDEEP (Ref. SBPLY/19/180501/000273). The funding agencies had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript
BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

A low-cost automated digital microscopy platform for automatic identification of diatoms

  • Salido Tercero, Jesús
  • Sánchez Bueno, Carlos
  • Ruiz-Santaquiteria Alegre, Jesús
  • Cristóbal Pérez, Gabriel
  • Blanco Lanza, Saúl
  • Bueno García, María Gloria
This article belongs to the Special Issue Advanced Intelligent Imaging Technology Ⅱ, [EN] Currently, microalgae (i.e., diatoms) constitute a generally accepted bioindicator of water quality and therefore provide an index of the status of biological ecosystems. Diatom detection for specimen counting and sample classification are two difficult time-consuming tasks for the few existing expert diatomists. To mitigate this challenge, in this work, we propose a fully operative low-cost automated microscope, integrating algorithms for: (1) stage and focus control, (2) image acquisition (slide scanning, stitching, contrast enhancement), and (3) diatom detection and a prospective specimen classification (among 80 taxa). Deep learning algorithms have been applied to overcome the difficult selection of image descriptors imposed by classical machine learning strategies. With respect to the mentioned strategies, the best results were obtained by deep neural networks with a maximum precision of 86% (with the YOLO network) for detection and 99.51% for classification, among 80 different species (with the AlexNet network). All the developed operational modules are integrated and controlled by the user from the developed graphical user interface running in the main controller. With the developed operative platform, it is noteworthy that this work provides a quite useful toolbox for phycologists in their daily challenging tasks to identify and classify diatoms, SI, This research was funded by the Spanish Government under the AQUALITAS-RETOS project with Ref. CTM2014-51907-C2-2-R-MINECO
BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

Automated Diatom Classification (Part A): Handcrafted Feature Approaches

  • Bueno García, María Gloria
  • Déniz Suárez, Óscar
  • Pedraza, Aníbal
  • Ruiz-Santaquiteria Alegre, Jesús
  • Salido Tercero, Jesús
  • Cristóbal Pérez, Gabriel
  • Borrego Ramos, María
  • Blanco Lanza, Saúl
This article belongs to the Special Issue Automated Analysis and Identification of Phytoplankton Images, [EN] This paper deals with automatic taxa identification based on machine learning methods. The aim is therefore to automatically classify diatoms, in terms of pattern recognition terminology. Diatoms are a kind of algae microorganism with high biodiversity at the species level, which are useful for water quality assessment. The most relevant features for diatom description and classification have been selected using an extensive dataset of 80 taxa with a minimum of 100 samples/taxon augmented to 300 samples/taxon. In addition to published morphological, statistical and textural descriptors, a new textural descriptor, Local Binary Patterns (LBP), to characterize the diatom’s valves, and a log Gabor implementation not tested before for this purpose are introduced in this paper. Results show an overall accuracy of 98.11% using bagging decision trees and combinations of descriptors. Finally, some phycological features of diatoms that are still difficult to integrate in computer systems are discussed for future work, SI, The authors acknowledge financial support of the Spanish Government under the Aqualitas-retos project (Ref. CTM2014-51907-C2-2-R-MINECO), http://aqualitas-retos.es/en/
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Contribución de congreso (ConferenceOutput)

Deep Learning Versus Classic Methods for Multi-taxon Diatom Segmentation

  • Ruiz-Santaquiteria, Jesús
  • Pedraza, Aníbal
  • Sánchez-Bueno, Carlos
  • Libreros, José A.
  • Salido, Jesús
  • Déniz, Óscar
  • Blanco, Saúl
  • Cristóbal, Gabriel
  • Bueno, Gloria
IbPRIA 2019,Madrid, Spain. July 1-4 2019. -- http://www.ibpria.org/2019/. -- Part of the Lecture Notes in Computer Science book series (LNCS, volume 11867) Also part of the Image Processing, Computer Vision, Pattern Recognition, and Graphics book sub series (LNIP, volume 11867), Diatom identification is a crucial process to estimate water quality, which is essential in biological studies. This process can be auto- mated with machine learning algorithms. For this purpose, a dataset with 10 common taxa is collected, with annotations provided by an expert diatomist. In this work, a comparison of the classical state-of-the-art gen- eral purpose methods along with two different deep learning approaches is carried out. The classical methods are based on Viola-Jones and scale and curvature invariant ridge object detectors. The deep learning based methods are Semantic Segmentation and YOLO. This is the first time that Viola-Jones and Semantic Segmentation techniques are applied and compared for diatom segmentation in microscopic images containing sev- eral taxon shells. While all methods provide relatively good results in specific species, the deep learning approaches are consistently better in terms of sensitivity and specificity (up to 0.99 for some taxa) and up to 0.86 precision., The authors acknowledge financial support of the Spanish Government under the Aqualitas-retos project (Ref. CTM2014-51907-C2-R-MINECO).
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Diatom Classification Including Morphological Adaptations Using CNNs

  • Sánchez, Carlos
  • Vallez, Noelia
  • Bueno, Gloria
  • Cristóbal, Gabriel
12 pags., 5 figs., 4 tabs. -- 9th Iberian Conference on Pattern Recognition and Image Analysis IbPRIA 2019, Madrid, Spain, 1-4 July 2019, Abstract. Diatoms are a major group of aquatic microalgae. They are widely used in different fields such as environmental studies to estimate water quality. This paper presents the use of convolutional neural net- works (CNNs) to identify diatoms during their life cycle. This life cycle involves morphological and other changes to the diatom frustule adding intraclass variance and making harder the classification task. The per- formance of CNNs is compared against a classical image classification scheme (i.e., feature extraction and classification) using a 14 classes dataset with a total number of 1085 images ranging from 40 to 120 images per class. Classification accuracy was 99.07% and 99.7% for CNNs and classical methods respectively., The authors acknowledge financial support of the Spanish Government under the Aqualitas-retos project (Ref. CTM2014-51907-C2-R-MINECO)
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Contribución de congreso (ConferenceOutput)

Pencil Drawing of Microscopic Images Through Edge Preserving Filtering

  • Singh, H.
  • Sánchez, Carlos
  • Cristóbal, Gabriel
  • Bueno, Gloria
IbPRIA 2019, Madrid, Spain. July 1-4, Automatic diatom identification approaches have revealed remarkable abilities to tackle the challenges of water quality assessment and other environmental issues. Scientists often analyze the taxonomic characters of the target taxa for automatic identification. In this process the digital photographs, sketches or drawings are recorded to analyze the shape and size of the frustule, the arrangement of striae, the raphe end- ings, and the striae density. In this paper, we describe two new methods for producing drawings of different diatom species at any stage of their life cycle development that can also be useful for future reference and comparisons. We attempt to produce drawings of diatom species using Edge-preserving Multi-scale Decomposition (EMD). The edge preserv- ing smoothing property of Weighted Least Squares (WLS) optimization framework is used to extract high-frequency details. The details extracted from two-scale decomposition are transformed to drawings which help in identifying possible striae patterns from diatom images. To analyze the salient local features preserved in the drawings, the Scale Invari- ant Feature Transform (SIFT) model is adopted for feature extraction. The generated drawings help to identify certain unique taxonomic and morphological features that are necessary for the identification of the diatoms. The new methods have been compared with two alternative pencil drawing techniques showing better performance for details preservation., The authors acknowledge financial support of the Spanish Government under the Aqualitas-retos project (Ref. CTM2014-51907-C2-R-MINECO). The authors thank Saúl Blanco for providing subjective evaluation of the results.