A Python toolbox for Automatic Face Alignment (AFA)

2021 ◽  
Author(s):  
Carl Michael Gaspar ◽  
Oliver G. B. Garrod

We describe AFA, an open-source Python package for automating the most common step in the preparation of facial stimuli for behavioral and neuro-imaging experiments – spatial alignment of faces (https://github.com/SourCherries/auto-face-align ). Face alignment is also important in the analysis of image statistics, and as a preprocessing step for machine learning. Automation of face alignment via AFA provides a reliable and efficient alternative to the very common practice of manual image-editing in graphics editors like Photoshop. As an open-source Python package, AFA encourages a clear and transparent specification of experimental method. AFA is based on facial landmark detection that is powered by the reliable and open-source DLIB library; and critical alignment code based on Generalized Procrustes Analysis (GPA) has been extensively unit-tested. AFA documentation and modularity provides opportunity for the modification and extensibility of AFA by the scientific community. As examples, we include functions for automatically generating image apertures that conceal areas outside the inner face; for image morphing between facial identities; and for shape-based averaging of facial identity. All of these are examples of stimulus preparation that have previously required manual landmark selection.

Author(s):  
V.N. Voloshin ◽  
I.S. Voloshina ◽  
I.Yu. Vash

The aim of the paper is to study thymus variability in white rats, which were exposed to formaldehyde, and to compare these data with the indicators in control animals. Materials and Methods. The trial enrolled 72 white male rats, initial body weight 40–50 g. The animals were divided into 2 groups (36 rats in each). The first group consisted of control rats. Animals of the second group were exposed to formaldehyde inhalation, 2.766 mg/m3. To characterize the variability of the organ size, centroids were determined. The superposition of landmark configurations was performed using the generalized Procrustes analysis method, MorphoJ 1.06d program. The principal component analysis and canonical analysis of the obtained data were carried out. Results. One-Way ANOVA revealed a high level of intergroup differences in Procrust distance (F=1.34; p<0.0001). The significant effect of the duration of formaldehyde exposure on centroid size was established. The Kruskal-Wallis criterion was 19.778 (p=0.0014). The analysis of the principal components indicated that each of the first 10 components stands for more than 1 % of Procrustes coordinate variance. In this case, the first 7 components compatibly explain 91.398 % of thymus variability. The proportion of the first main component to the total variance of the Procrustes coordinates is 40.236 %. PC1 (-) shows changes in the thymus shape, mostly affecting the tops of its lobes, the middle part of the right boundary and the entire left thymus boundary. The scattering ellipses of the thymus ordinates in rats exposed to formaldehyde, in the first two canonical variables are located higher than those in the control animals. Conclusion. Formaldehyde inhalation leads to thymus changes in white rat. The most significant differences with control data are determined along the second canonical variable. Keywords: thymus, form, rat, formaldehyde, geometric morphometry. Цель. Изучение изменчивости формы тимуса белых крыс, находившихся в условиях влияния формальдегида, и сравнение этих данных с показателями, полученными у контрольных животных. Материалы и методы. Работа выполнена на 72 белых крысах-самцах с начальной массой тела 40–50 г. Животные были разделены на 2 серии (по 36 крыс). Первую серию составляли контрольные крысы. Животные второй серии подвергались ингаляционному воздействию формальдегида (ФА) в концентрации 2,766 мг/м3. Для характеристики изменчивости размеров органов определяли размер их центроидов. Процедуру суперимпозиции конфигураций ландмарок выполняли методом генерализованного прокрустова анализа с использованием программы MorphoJ 1.06d. Проводили анализ главных компонент и канонический анализ полученных данных. Результаты. Однофакторный дисперсионный анализ выявил высокий уровень межгрупповых различий по показателю прокрустовых расстояний (F=1,34; р<0,0001). Установлено значительное влияние продолжительности нахождения животных в условиях воздействия ФА на размер центроида. Критерий Краскела–Уоллиса составил 19,778 (р=0,0014). Анализ главных компонент указывал на то, что каждая из первых 10 компонент объясняет более 1 % дисперсии прокрустовых координат. При этом первые 7 компонент совместно объясняют 91,398 % изменчивости формы тимуса. Вклад первой главной компоненты в общую дисперсию прокрустовых координат составляет 40,236 %. РС1 (–) показывает изменения формы тимуса, в большей степени затрагивающие верхушки его долей, среднюю часть правого контура и весь левый контур тимуса. Эллипсы рассеивания ординат тимусов, принадлежащих крысам, подвергавшимся влиянию ФА, в пространстве первых двух канонических переменных расположены выше по отношению к таковым контрольных животных. Заключение. Ингаляционное воздействие формальдегида приводит к изменению формы тимуса белых крыс. Наибольшие различия с контрольными данными определяются вдоль второй канонической переменной. Ключевые слова: тимус, форма, крыса, формальдегид, геометрическая морфометрия.


2021 ◽  
Vol 6 (1) ◽  
Author(s):  
Jing Wui Yeoh ◽  
Neil Swainston ◽  
Peter Vegh ◽  
Valentin Zulkower ◽  
Pablo Carbonell ◽  
...  

Abstract Advances in hardware automation in synthetic biology laboratories are not yet fully matched by those of their software counterparts. Such automated laboratories, now commonly called biofoundries, require software solutions that would help with many specialized tasks such as batch DNA design, sample and data tracking, and data analysis, among others. Typically, many of the challenges facing biofoundries are shared, yet there is frequent wheel-reinvention where many labs develop similar software solutions in parallel. In this article, we present the first attempt at creating a standardized, open-source Python package. A number of tools will be integrated and developed that we envisage will become the obvious starting point for software development projects within biofoundries globally. Specifically, we describe the current state of available software, present usage scenarios and case studies for common problems, and finally describe plans for future development. SynBiopython is publicly available at the following address: http://synbiopython.org.


2021 ◽  
Author(s):  
Tom Winder ◽  
Conor Bacon ◽  
Jonathan Smith ◽  
Thomas Hudson ◽  
Tim Greenfield ◽  
...  

2017 ◽  
Vol 139 ◽  
pp. 320-329 ◽  
Author(s):  
Joshua Stuckner ◽  
Katherine Frei ◽  
Ian McCue ◽  
Michael J. Demkowicz ◽  
Mitsuhiro Murayama

1998 ◽  
Vol 9 (3) ◽  
pp. 111-114 ◽  
Author(s):  
Sijmen de Jong ◽  
Johannes Heidema ◽  
Henk C.M. van der Knaap

Author(s):  
Wei Hao Khoong

In this paper, we introduce deboost, a Python library devoted to weighted distance ensembling of predictions for regression and classification tasks. Its backbone resides on the scikit-learn library for default models and data preprocessing functions. It offers flexible choices of models for the ensemble as long as they contain the predict method, like the models available from scikit-learn. deboost is released under the MIT open-source license and can be downloaded from the Python Package Index (PyPI) at https://pypi.org/project/deboost. The source scripts are also available on a GitHub repository at https://github.com/weihao94/DEBoost.


Author(s):  
Gazel Ser

Generalized Procrustes Analysis (GPA) is a multivariate statistic method that is used at the evaluation of sensory analyses in the food industry. GPA provides benefit in terms of decreasing the difference between the panellists and bringing the data obtained from different panellists together. In this study, the aim was to determine the effect of a pre-slaughter fasting period on sensory characteristics of lambs fed with different rations using GPA. Semi-trained panellists formed from twenty-six persons were requested for evaluation of the meat samples such as tenderness, juiciness, flavour and overall liking rated on a scale of 1(extremely dislike) to 9 (extremely good). The first two factors obtained by GPA explained 66.74% of total variability. As a result of the analysis, it was determined that 12 h and 24 h fasting of lambs fed barley supplemented with alfalfa hay were less preferable when compared to lambs fed alfalfa hay only. In addition, lambs in both groups with 48 h fasting were preferred less by the panellists. In conclusion, GPA analysis provides useful data concerning the sensitivity of each panellist in a sensory panel test.


1994 ◽  
Vol 31 (1) ◽  
pp. 15-27 ◽  
Author(s):  
Jan-Benedict E.M. Steenkamp ◽  
Hans C.M. Van Trijp ◽  
Jos M.F. Ten Berge

The authors describe a compositional perceptual mapping procedure, unrestricted attribute-elicitation mapping (UAM), which allows consumers to describe and rate the brands in their own terminology and thus relaxes the restrictive assumptions of traditional compositional mapping techniques regarding the structure and interpretation of the set of attributes. They compare the performance of three estimation techniques for constructing a group space based on the idiosyncratic data, namely, INDSCAL, CANCOR, and generalized procrustes analysis (GPA). Their findings indicate that the three estimation techniques perform about equally well. UAM also is compared with traditional compositional mapping. They find that UAM is superior on fit of the solution, interpretability, and sample reliability. UAM probably holds an edge with respect to data collection. Traditional compositional mapping is superior on ease of data analysis. No major difference was found on predictive validity and structural reliability.


2018 ◽  
Vol 98 (8) ◽  
pp. 1991-1998
Author(s):  
A. L. Ibáñez ◽  
L. A. Jawad

New Zealand rattail fish are of great interest both to biologists who study their phylogenetics and in fisheries. In contrast, their morphological evolution is little studied and poorly understood. Geometric morphometric methods based on scale shape were applied in this study to determine differences among species and genera. Scale shapes were described using seven landmarks, the coordinates of which were subjected to a generalized Procrustes analysis, followed by a principal components analysis. A cross-validated discriminant analysis was applied to assess and compare the size-shape (centroid size plus shape variables) efficacy in the species and the discrimination of the genera. Two main phenetic groups were identified: cluster no. 1 with eight species and cluster no. 2 with six species. Coelorhinchus aspercephalus and Mesovagus antipodum were more separated from the other species in the first cluster. The cross-validated canonical discriminant analysis correctly classified 74% at the genus level, with most misclassifications occurring between Coelorhinchus and Coryphaenoides, whereas the best classified genera were Mesovagus and Trachyrincus. The discrimination of correctly classified species ranged from 41.2 to 100%. The highest correct classification rates were recorded for Coryphaenoides armatus, Coelorhinchus innotabilis, Trachyrincus longirostris and Mesovagus antipodum.


Sign in / Sign up

Export Citation Format

Share Document