María Teresa García-Ordás

Texture and moments-based classification of the acrosome integrity of boar spermatozoa images

The automated assessment of the sperm quality is an important challenge in the veterinary field. In this paper, we explore how to describe the acrosomes of boar spermatozoa using image analysis so that they can be automatically categorized as intact or damaged. Our proposal aims at characterizing the acrosomes by means of texture features. The texture is described using first order statistics and features derived from the co-occurrence matrix of the image, both computed from the original image and from the coefficients yielded by the Discrete Wavelet Transform. Texture descriptors are evaluated and compared with moments-based descriptors in terms of the classification accuracy they provide. Experimental results with a Multilayer Perceptron and the k-Nearest Neighbours classifiers show that texture descriptors outperform moment-based descriptors, reaching an accuracy of 94.93%, which makes this approach very attractive for the veterinarian community.

Adaptive local binary pattern with oriented standard deviation (ALBPS) for texture classification

AbstractA new method to describe texture images using a hybrid combination of local and global texture descriptors is proposed in this paper. In this regard, a new adaptive local binary pattern (ALBP) descriptor is presented in order to carry out the local description. It is built by adding oriented standard deviation information to an ALBP descriptor in order to achieve a more complete representation of the images, and hence, it has been called adaptive local binary pattern with oriented standard deviation (ALBPS). Regarding semen vitality assessment, ALBPS outperformed previous literature works with an 81.88% accuracy and also yielded higher hit rates than the LBP and ALBP baseline methods. Concerning the global description of the images, several classical texture algorithms were tested and a descriptor based on wavelet transform and Haralick feature extraction (wavelet concurrent feature 13 (WCF13)) obtained the best results. Both local and global descriptors were combined, and the classification was carried out with a support vector machine. Two data sets have been evaluated: textures under varying illumination, pose and scale (KTH-TIPS) 2a data set and a second spermatozoa boar data set used to distinguish between dead or alive sperm heads. Therefore, our proposal is novel in three ways. First, a new local feature extraction method ALBPS is introduced. Second, a hybrid method combining the proposed local ALBPS and a global descriptor is presented, outperforming our first approach and all other methods evaluated for this problem. Third, texture classification accuracy is greatly improved with the two former texture descriptors presented. F score and accuracy values were computed in order to measure the performance. The best overall result was yielded by combining ALBPS with WCF13, reaching an F score = 0.886 and an accuracy of 85.63% in the spermatozoa data set and an 84.45% of hit rate in the KTH-TIPS 2a.

Curvelet-based texture description to classify intact and damaged boar spermatozoa

The assessment of boar sperm head images according to their acrosome status is a very important task in the veterinary field. Unfortunately it can only be performed manually, which is slow, non-objective and expensive. It is important to provide companies an automatic and reliable method to perform this task. In this paper a new method which uses texture descriptors based on the Curvelet Transform is proposed. Its performance has been compared with other texture descriptors based on the Wavelet transform, and also with moments based descriptors, as they seem to be successful for this problem. Texture descriptors performed better, and curvelet-based ones achieved the best hit rate (97%) and area under the ROC curve (0.99).

aZIBO: A New Descriptor Based in Shape Moments and Rotational Invariant Features

In this work, a descriptor called a ZIBO (absolute Zernike moments with Invariant Boundary Orientation) that describes the shape of objects using the module of Zernike moments and the edge features obtained from an almost rotational invariant version of the Edge Gradient Co-occurrence Matrix (EGCM) is proposed. The two descriptors obtained, the Zernike module as global descriptor and the new version of EGCM as local one, are used to characterize images from three different datasets, Kimia99, MPEG2 and MPEG7. Later on, the concatenation of both local and global descriptors was evaluated using kNN with City block and Chi-square distance metrics. Also, the descriptors are assessed separately with a weight-based method, being the results obtained compared with the ones reached by the baseline method, ZMEG (Zernike Moment Edge Gradient). Using MPEG7, which is the most challenging dataset, and the weight-based classifier, this proposal obtained a success rate of 78.29%, outperforming the 75.86% achieved by ZMEG method. With the MPEG2 dataset, results were even better with an 81.00% of success rate against 77.25% of ZMEG.

Evaluation of Different Metrics for Shape Based Image Retrieval Using a New Contour Points Descriptor

In this paper, an image shape retrieval method was evaluated using Euclidean, Intersect, Hamming and Cityblock distances and different kinds of k-nearest neighbours classifiers such as the original kNN, mean distance kNN and Weighted kNN. Shapes were described using a new method based on the description of the contour points, CPDH36R, obtaining better results than with the original CPDH shape descriptor. The efficiency in the retrieval was tested using Kimia99, Kimia25, MPEG7 and MPEG2 datasets obtaining an 84% of success rate in Kimia25, 94% in Kimia99, 91% in MPEG2 and 82% in MPEG7 datasets using our CPDH36R method, cityblock distance and original kNN against the 68%, 91%, 74% and 59% respectively obtained using the original CPDH. The greatest difference between the original method and our proposal can be seen clearly using MPEG2 dataset. Another advantage of our retrieval method, apart from the success rate, is the computational cost which is clearly better than the one achieved with the original Earth Mover Distance classifier used in the CPDH original method.

Vitality assessment of boar sperm using N concentric squares resized (NCSR) texture descriptor in digital images

Two new textural descriptor, named N Concentric Squares Resized (NCSR) and N Concentric Squares Histogram (NCSH), have been proposed. These descriptors were used to classify 472 images of alive spermatozoa heads and 376 images of dead spermatozoa heads. The results obtained with these two novel descriptors have been compared with a number of classical descriptors such as Haralick, Pattern Spectrum, WSF, Zernike, Flusser and Hu. The feature vectors computed have been classified using kNN and a backpropagation Neural Network. The error rate obtained for NCSR with N = 11 was of 23.20% outperforms the rest of descriptors. Also, the area under the ROC curve (AUC) and the values observed in the ROC curve indicates the performance of the proposed descriptor is better than the others texture description methods.

Evaluation of LBP Variants Using Several Metrics and kNN Classifiers

In this paper, we demonstrate that the Adaptive Local Binary Pattern with oriented Standard deviation ALBPS method outperforms the original local binary pattern LBP as well as some of its most recent variants: Adaptive Local Binary Pattern ALBP, Complete Local Binary Pattern CLBP and Local Binary Pattern Variance LBPV. All the descriptors have been tested using two different dataset, KTH-TIPS 2a, a challenging multiclass dataset for material recognition and a binary sperm dataset for vitality classification. Three variants of the non parametric method of nearest neighbours combined with four metric distances have been used in the retrieval step in order to draw a more decisive conclusion. Best results were achieved when describing the images with ALBPS in both datasets. In regard to the KTH-TIPS 2a, the best performance is obtained using the weighted kNN with a 61.47% of hit rate using ALBPS and Chi Square distance, outperforming the ALBP in 1,07% and the original LBP in 6,76%. In relation to the binary sperm dataset, the best result was obtained with ALBPS and a kNN classifier k=9, reaching a 72.66% of hit rate using the Chi Square metric, outperforming the original LBP in 22,47% and the ALBP in 1,22%. In the latter case, the weighted kNN did not improve the results achieved using just kNN. Taking this results into account, we can determine that ALBPS has more discriminant power for image retrieval than the rest of the tested LBP variants in different image contexts.

Automatic Tampering Detection in Spliced Images with Different Compression Levels

In this paper, we introduce a blind tampering detection method based on JPEG ghosts [3] capable of detecting tampering when it is created by splicing regions with different compression levels in an image. Given an image, a set of re-compressions of that image is generated and used to extract a feature vector to train a Support Vector Machine classifier. We used two different datasets in our experiments. The first one, extracted from Columbia Uncompressed Image Splicing Detection, was used to compare results with other works. Our method outperformed the previous ones when dealing with small tampered regions and similar qualities, offering hit rates above 97% (100% in the case of non-tampered images). With the second dataset, CASIA1 Tampered Image Detection Evaluation Dataset, our method offered a hit rate of 98.71% when discerning between the original and the spliced image, with just a 0.44% of non-tampered images wrongly classified.

Combining shape and contour features to improve tool wear monitoring in milling processes

In this paper, a new system based on combinations of a shape descriptor and a contour descriptor has been proposed for classifying inserts in milling processes according to their wear level following a computer vision based approach. To describe the wear region shape we have proposed a new descriptor called ShapeFeat and its contour has been characterized using the method BORCHIZ that, to the best of our knowledge, achieves the best performance for tool wear monitoring following a computer vision-based approach. Results show that the combination of BORCHIZ with ShapeFeat using a late fusion method improves the classification performance significantly, obtaining an accuracy of 91.44% in the binary classification (i.e. the classification of the wear as high or low) and 82.90% using three target classes (i.e. classification of the wear as high, medium or low). These results outperform the ones obtained by both descriptors used on their own, which achieve accuracies of 88.70 and 80.67% for two and three classes, respectively, using ShapeFeat and 87.06 and 80.24% with B-ORCHIZ. This study yielded encouraging results for the manufacturing community in order to classify automatically the inserts in terms of their wear for milling processes.

Assessing Feature Selection Techniques for a Colorectal Cancer Prediction Model

Risk prediction models for colorectal cancer play an important role to identify people at higher risk of developing this disease as well as the risk factors associated with it. Feature selection techniques help to improve the prediction model performance and to gain insight in the data itself. The assessment of the stability of feature selection/ranking algorithms becomes an important issue when the aim is to analyze the most relevant features. This work assesses several feature ranking algorithms in terms of performance and robustness for a set of risk prediction models. Experimental results demonstrate that stability and model performance should be studied jointly as RF turned out to be the most stable algorithm but outperformed by others in terms of model performance while SVM-wrapper and the Pearson correlation coefficient are moderately stable while achieving good model performance.