A database for automatic classification of forest species

Martins, Jefferson Gustavo; Oliveira, Luiz S.; Nisgoski, Silvana; Sabourin, Robert

doi:10.1007/s00138-012-0417-5

Cited by 81 publications

(65 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Macroscopic [18] and Microscopic forest species databases [17] are also used to test our approach on larger texture images (respectively 3264x2448 and 1024x768). We resize the images of both datasets to 640x640.…”

Section: Datasetsmentioning

confidence: 99%

Using filter banks in Convolutional Neural Networks for texture classification

Andrearczyk

Whelan

2016

Pattern Recognition Letters

243

156

View full text Add to dashboard Cite

Deep learning has established many new state of the art solutions in the last decade in areas such as object, scene and speech recognition. In particular Convolutional Neural Network (CNN) is a category of deep learning which obtains excellent results in object detection and recognition tasks. Its architecture is indeed well suited to object analysis by learning and classifying complex (deep) features that represent parts of an object or the object itself. However, some of its features are very similar to texture analysis methods. CNN layers can be thought of as filter banks of complexity increasing with the depth. Filter banks are powerful tools to extract texture features and have been widely used in texture analysis. In this paper we develop a simple network architecture named Texture CNN (T-CNN) which explores this observation. It is built on the idea that the overall shape information extracted by the fully connected layers of a classic CNN is of minor importance in texture analysis. Therefore, we pool an energy measure from the last convolution layer which we connect to a fully connected layer. We show that our approach can improve the performance of a network while greatly reducing the memory usage and computation.

show abstract

Section: Datasetsmentioning

confidence: 99%

Using filter banks in Convolutional Neural Networks for texture classification

Andrearczyk

Whelan

2016

Pattern Recognition Letters

243

156

View full text Add to dashboard Cite

show abstract

“…Several methods such as the gray level co-occurrence matrix (GLCM) [13,14], local binary pattern (LBP) [15,16], and higher order local autocorrelation (HLAC) [17] have been tested to extract features from wood images. Computer vision is a part of the diverse field of artificial intelligence, and is one of the technologies with the most potential.…”

Section: Introductionmentioning

confidence: 99%

Automated identification of Lauraceae by scale-invariant feature transform

et al. 2017

View full text Add to dashboard Cite

An image dataset of the cross-sectional optical micrographs of the Lauraceae species including 39 species in 11 genera, capturing at least one full annual ring, was investigated by scale-invariant feature transform (SIFT), a computer vision-based feature extraction algorithm. We found an image of 900 × 900-pixel size at a pixel resolution of ca. 3 µm, corresponding to the actual size of 2.65 × 2.65 mm 2 , as the minimum requirement for the image dataset in terms of the accuracy of the recognition at both the genus and species levels. Among the several classifiers investigated, the linear discriminant analysis (LDA) presented the best performance reaching a maximum of 89.4% in the genus with a species identification of approximately 96.3%. Cluster analysis of all the SIFT descriptors for each image yielded practical information regarding the descriptors; they recognize selectively the cell lumina, cell corners, vessels, and axial and ray parenchyma cells. Therefore, the difference between the genus or species levels was determined per the variation in the quantities of these computer-based properties. Another clustering approach, the hierarchal dendrogram, was applied to visualize the numerical distances between the genus and species. Interestingly, even Machilus and Phoebe, which are difficult to distinguish by conventional visual inspection, are quite distantly classified at the genus level. In contrast, some species in Cinnamomum, Machilus and Litsea were categorized into different subgroups rather than the original genus. Microscopic wood identification is found to be possible at the genus level; however, the numerical dataset of the morphological features has various overlapping clusters, causing the genus-level identification of the Lauraceae to be more difficult than species-level identification.

show abstract

“…Recentes pesquisas têm sido feitas para analisar computacionalmente imagens de madeira para identificar as suas espécies (CUI; ZHAI; WANG, 2013), utilizando imagens macroscópi-cas (BREMANANTH; NITHYA; SAIPRIYA, 2009;YU et al, 2009;YUSOF, 2011;RUBIYAHYUSOF;ANISSALWAMOHDKHAIRUDDIN, 2011;YU-SOF;KHAIRUDDIN, 2013b;KHAIRUDDIN, 2013a;ZHAO, 2013;ZHAO;CHEN, 2014b;ZHAO;CHEN, 2014a;FILHO et al, 2014) e microscópicas (MALLIK et al, 2011;GURAU et al, 2013;GUANG-SHENG;MARTINS et al, 2013;SABOURIN, 2012;CAVALIN et al, 2013). No entanto, apesar de alguns estudos mostrarem resultados satisfatórios com uma boa taxa de sucesso, eles são baseados em experimentos utilizando poucas espécies, em alguns casos até 10 espécies (BREMANANTH; NITHYA; SAIPRIYA, 2009;ZHAO, 2013;ZHAO;CHEN, 2014b;ZHAO;CHEN, 2014a;MALLIK et al, 2011).…”

Section: Identificação De Espécies De Madeiraunclassified

“…Por outro lado, algumas pesquisas fazem uso de características morfológicas (KHAIRUDDIN; KHALID; YUSOF, 2011; KHALID; RUBIYAHYUSOF; ANISSALWAMOHDKHAIRUDDIN, 2011;KHAIRUDDIN, 2013b;KHAIRUDDIN, 2013a;GURAU et al, 2013;GUANG-SHENG;, tais como propriedades estatísticas de distribuição de poros, que são dependentes da segmentação (GUANG-SHENG; PENG, 2013), obtendo resultados instáveis, uma vez que a segmentação ainda é um campo aberto de investigação HUANG;XU, 2010;. Devido à limitação para segmentar imagens, a textura tem se mostrado um campo promissor para a identificação de espécies de madeira (FILHO et al, 2014;MARTINS et al, 2013;SABOURIN, 2012;CAVALIN et al, 2013;ZHAO;CHEN, 2014a;ZHAO;CHEN, 2014b). Em Martins et al (2013), Martins, Oliveira e Sabourin (2012) e Cavalin et al (2013) foram utilizadas características de textura para identificar 112 espécies de madeira da flora brasileira, utilizando somente seções transversais microscópicas.…”

Section: Identificação De Espécies De Madeiraunclassified

“…Devido à limitação para segmentar imagens, a textura tem se mostrado um campo promissor para a identificação de espécies de madeira (FILHO et al, 2014;MARTINS et al, 2013;SABOURIN, 2012;CAVALIN et al, 2013;ZHAO;CHEN, 2014a;ZHAO;CHEN, 2014b). Em Martins et al (2013), Martins, Oliveira e Sabourin (2012) e Cavalin et al (2013) foram utilizadas características de textura para identificar 112 espécies de madeira da flora brasileira, utilizando somente seções transversais microscópicas. No entanto, poucos estudos têm relatado a análise de textura de imagens de seção microscópicas transversais para a identificação de madeira.…”

Section: Identificação De Espécies De Madeiraunclassified

See 1 more Smart Citation

Reconhecimento de padrões heterogêneos e suas aplicações em biologia e nanotecnologia

Silva¹

View full text Add to dashboard Cite

A database for automatic classification of forest species

Cited by 81 publications

References 10 publications

Using filter banks in Convolutional Neural Networks for texture classification

Using filter banks in Convolutional Neural Networks for texture classification

Automated identification of Lauraceae by scale-invariant feature transform

Reconhecimento de padrões heterogêneos e suas aplicações em biologia e nanotecnologia

Contact Info

Product

Resources

About