Logo: to the web site of Uppsala University

uu.sePublications from Uppsala University
Change search
Link to record
Permanent link

Direct link
Publications (10 of 52) Show all publications
Wang, X. M., Lind, M. & Bingham, G. P. (2020). A stratified process for the perception of objects: From optical transformations to 3D relief structure to 3D similarity structure to slant or aspect ratio. Vision Research, 173, 77-89
Open this publication in new window or tab >>A stratified process for the perception of objects: From optical transformations to 3D relief structure to 3D similarity structure to slant or aspect ratio
2020 (English)In: Vision Research, ISSN 0042-6989, E-ISSN 1878-5646, Vol. 173, p. 77-89Article in journal (Refereed) Published
Abstract [en]

Previously, we developed a stratified process for slant perception. First, optical transformations in structure-from-motion (SFM) and stereo were used to derive 3D relief structure (where depth scaling remains arbitrary). Second, with sufficient continuous perspective change (>= 45 degrees), a bootstrap process derived 3D similarity structure. Third, the perceived slant was derived. As predicted by theoretical work on SFM, small visual angle (< 5 degrees) viewing requires non-coplanar points. Slanted surfaces with small 3D cuboids or tetrahedrons yielded accurate judgment while planar surfaces did not. Normally, object perception entails non-coplanar points. Now, we apply the stratified process to object perception where, after deriving similarity structure, alternative metric properties of the object can be derived (e.g. slant of the top surface or width-to-depth aspect ratio). First, we tested slant judgments of the smooth planar tops of three different polyhedral objects. We tested rectangular, hexagonal, and asymmetric pentagonal surfaces, finding that symmetry was required to determine the direction of slant (AP&P, 2019, https://doi.org/10.3758/s13414-019-01859-5). Our current results replicated the previous findings. Second, we tested judgments of aspect ratios, finding accurate performance only for symmetric objects. Results from this study suggest that, first, trackable non-coplanar points can be attained in the form of 3D objects. Second, symmetry is necessary to constrain slant and aspect ratio perception. Finally, deriving 3D similarity structure precedes estimating object properties, such as slant or aspect ratio. Together, evidence presented here supports the stratified bootstrap process for 3D object perception. Statement of significance: Planning interactions with objects in the surrounding environment entails the perception of 3D shape and slant. Studying ways through which 3D metric shape and slant can be perceived accurately by moving observers not only sheds light on how the visual system works, but also provides understanding that can be applied to other fields, like machine vision or remote sensing. The current study is a logical extension of previous studies by the same authors and explores the roles of large continuous perspective changes, relief structure, and symmetry in a stratified process for object perception.

Place, publisher, year, edition, pages
PERGAMON-ELSEVIER SCIENCE LTD, 2020
Keywords
Object perception, Bootstrap process, Slant, Shape perception, Stereomotion, Structure-from-motion, Symmetry
National Category
Ophthalmology Neurosciences Neurology Psychology
Identifiers
urn:nbn:se:uu:diva-418856 (URN)10.1016/j.visres.2020.04.014 (DOI)000542624900008 ()32480110 (PubMedID)
Available from: 2020-09-04 Created: 2020-09-04 Last updated: 2020-09-04Bibliographically approved
Wang, X. M., Lind, M. & Bingham, G. P. (2020). Bootstrapping a better slant: A stratified process for recovering 3D metric slant. Attention, Perception & Psychophysics, 82(3), 1504-1519
Open this publication in new window or tab >>Bootstrapping a better slant: A stratified process for recovering 3D metric slant
2020 (English)In: Attention, Perception & Psychophysics, ISSN 1943-3921, E-ISSN 1943-393X, Vol. 82, no 3, p. 1504-1519Article in journal (Refereed) Published
Abstract [en]

Lind et al. (Journal of Experimental Psychology: Human Perception and Performance, 40 (1), 83, 2014) proposed a bootstrap process that used right angles on 3D relief structure, viewed over sufficiently large continuous perspective change, to recover the scaling factor for metric shape. Wang, Lind, and Bingham (Journal of Experimental Psychology: Human Perception and Performance, 44(10), 1508-1522, 2018) replicated these results in the case of 3D slant perception. However, subsequent work by the same authors (Wang et al., 2019) suggested that the original solution could be ineffective for 3D slant and presented an alternative that used two equidistant points (a portion of the original right angle). We now describe a three-step stratified process to recover 3D slant using this new solution. Starting with 2D inputs, we (1) used an existing structure-from-motion (SFM) algorithm to derive the object’s 3D relief structure and (2) applied the bootstrap process to it to recover the unknown scaling factor, which (3) was then used to produce a slant estimate. We presented simulations of results from four previous experiments (Wang et al., 2018, 2019) to compare model and human performance. We showed that the stratified process has great predictive power, reproducing a surprising number of phenomena found in human experiments. The modeling results also confirmed arguments made in Wang et al. (2019) that an axis of mirror symmetry in an object allows observers to use the recovered scaling factor to produce an accurate slant estimate. Thus, poor estimates in the context of a lack of symmetry do not mean that the scaling factor has not been recovered, but merely that the direction of slant was ambiguous.

Keywords
Bootstrap process, Geographical slant perception, Affine geometry, Stereomotion, Structure-from-motion, Symmetry
National Category
Computer Sciences
Identifiers
urn:nbn:se:uu:diva-418784 (URN)10.3758/s13414-019-01860-y (DOI)000541113500044 ()31506917 (PubMedID)
Available from: 2020-09-03 Created: 2020-09-03 Last updated: 2020-09-03Bibliographically approved
Hast, A. & Lind, M. (2020). Ensembles and Cascading of Embedded Prototype Subspace Classifiers. Journal of WSCG, 28(1/2), 89-95
Open this publication in new window or tab >>Ensembles and Cascading of Embedded Prototype Subspace Classifiers
2020 (English)In: Journal of WSCG, ISSN 1213-6972, E-ISSN 1213-6964, Vol. 28, no 1/2, p. 89-95Article in journal (Refereed) Published
Abstract [en]

Deep learning approaches suffer from the so called interpretability problem and can therefore be very hard to visualise. Embedded Prototype Subspace Classifiers is one attempt in the field of explainable AI, which is both fast and efficient since it does not require repeated learning epochs and has no hidden layers. In this paper we investigate how ensembles and cascades of ensembles perform on some popular datasets. The focus is on handwritten data such as digits, letters and signs. It is shown how cascading can be efficiently implemented in order to both increase accuracy as well as speed up the classification.

Keywords
Subspaces, Ensembles, Cascading, Embedded Prototypes, Neural Networks, Deep Learning.
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:uu:diva-416637 (URN)10.24132/JWSCG.2020.28.11 (DOI)
Projects
q2b
Available from: 2020-07-25 Created: 2020-07-25 Last updated: 2020-08-12Bibliographically approved
Wang, X. M., Lind, M. & Bingham, G. P. (2020). Symmetry mediates the bootstrapping of 3-D relief slant to metric slant. Attention, Perception & Psychophysics, 82(3), 1488-1503
Open this publication in new window or tab >>Symmetry mediates the bootstrapping of 3-D relief slant to metric slant
2020 (English)In: Attention, Perception & Psychophysics, ISSN 1943-3921, E-ISSN 1943-393X, Vol. 82, no 3, p. 1488-1503Article in journal (Refereed) Published
Abstract [en]

Empirical studies have always shown 3-D slant and shape perception to be inaccurate as a result of relief scaling (an unknown scaling along the depth direction). Wang, Lind, and Bingham (Journal of Experimental Psychology: Human Perception and Performance, 44(10), 1508–1522, 2018) discovered that sufficient relative motion between the observer and 3-D objects in the form of continuous perspective change (≥45°) could enable accurate 3-D slant perception. They attributed this to a bootstrap process (Lind, Lee, Mazanowski, Kountouriotis, & Bingham in Journal of Experimental Psychology: Human Perception and Performance, 40(1), 83, 2014) where the perceiver identifies right angles formed by texture elements and tracks them in the 3-D relief structure through rotation to extrapolate the unknown scaling factor, then used to convert 3-D relief structure to 3-D Euclidean structure. This study examined the nature of the bootstrap process in slant perception. In a series of four experiments, we demonstrated that (1) features of 3-D relief structure, instead of 2-D texture elements, were tracked (Experiment 1); (2) identifying right angles was not necessary, and a different implementation of the bootstrap process is more suitable for 3-D slant perception (Experiment 2); and (3) mirror symmetry is necessary to produce accurate slant estimation using the bootstrapped scaling factor (Experiments 3 and 4). Together, the results support the hypothesis that a symmetry axis is used to determine the direction of slant and that 3-D relief structure is tracked over sufficiently large perspective change to produce metric depth. Altogether, the results supported the bootstrap process.

Keywords
Bootstrap process, Geographical slant perception, Affine geometry, Stereomotion, Structure from motion, Skew symmetry
National Category
Computer Sciences
Identifiers
urn:nbn:se:uu:diva-418782 (URN)10.3758/s13414-019-01859-5 (DOI)000541113500043 ()31502187 (PubMedID)
Available from: 2020-09-04 Created: 2020-09-04 Last updated: 2020-09-04Bibliographically approved
Hast, A., Lind, M. & Vats, E. (2019). Embedded Prototype Subspace Classification: A subspace learning framework. In: Computer Analysis of Images and Patterns, CAIP 2019, PT II: . Paper presented at The 18th International Conference on Computer Analysis of Images and Patterns, CAIP 2019, September 2–6,2019, Salerno, Italy (pp. 581-592). Springer
Open this publication in new window or tab >>Embedded Prototype Subspace Classification: A subspace learning framework
2019 (English)In: Computer Analysis of Images and Patterns, CAIP 2019, PT II, Springer, 2019, p. 581-592Conference paper, Published paper (Refereed)
Abstract [en]

Handwritten text recognition is a daunting task, due to complex characteristics of handwritten letters. Deep learning based methods have achieved significant advances in recognizing challenging handwritten texts because of its ability to learn and accurately classify intricate patterns. However, there are some limitations of deep learning, such as lack of well-defined mathematical model, black-box learning mechanism, etc., which pose challenges. This paper aims at going beyond the blackbox learning and proposes a novel learning framework called as Embedded Prototype Subspace Classification, that is based on the well-known subspace method, to recognise handwritten letters in a fast and efficient manner. The effectiveness of the proposed framework is empirically evaluated on popular datasets using standard evaluation measures.

Place, publisher, year, edition, pages
Springer, 2019
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 11679
Keywords
Handwritten text, Subspaces, Deep learning, t-SNE
National Category
Medical Image Processing Human Computer Interaction
Identifiers
urn:nbn:se:uu:diva-393257 (URN)10.1007/978-3-030-29891-3_51 (DOI)000558110900051 ()978-3-030-29891-3 (ISBN)978-3-030-29890-6 (ISBN)
Conference
The 18th International Conference on Computer Analysis of Images and Patterns, CAIP 2019, September 2–6,2019, Salerno, Italy
Available from: 2019-09-18 Created: 2019-09-18 Last updated: 2020-10-27Bibliographically approved
Hast, A., Lind, M. & Vats, E. (2019). Subspace Learning and Classification. In: Proc. 3rd Swedish Symposium on Deep Learning: . Paper presented at SSDL 2019, June 10–11, Norrköping, Sweden.
Open this publication in new window or tab >>Subspace Learning and Classification
2019 (English)In: Proc. 3rd Swedish Symposium on Deep Learning, 2019Conference paper, Poster (with or without abstract) (Other academic)
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:uu:diva-389451 (URN)
Conference
SSDL 2019, June 10–11, Norrköping, Sweden
Available from: 2019-07-14 Created: 2019-07-14 Last updated: 2019-07-22
Wang, X. M., Lind, M. & Bingham, G. P. (2018). Large continuous perspective change with noncoplanar points enables accurate slant perception. Journal of Experimental Psychology: Human Perception and Performance, 44(10), 1508-1522
Open this publication in new window or tab >>Large continuous perspective change with noncoplanar points enables accurate slant perception
2018 (English)In: Journal of Experimental Psychology: Human Perception and Performance, ISSN 0096-1523, E-ISSN 1939-1277, Vol. 44, no 10, p. 1508-1522Article in journal (Refereed) Published
National Category
Human Computer Interaction
Identifiers
urn:nbn:se:uu:diva-363204 (URN)10.1037/xhp0000553 (DOI)000445961700003 ()29927269 (PubMedID)
Available from: 2018-10-18 Created: 2018-10-18 Last updated: 2018-10-18Bibliographically approved
Fath, A. J., Lind, M. & Bingham, G. P. (2018). Perception of time to contact of slow- and fast-moving objects using monocular and binocular motion information. Attention, Perception & Psychophysics, 80(6), 1584-1590
Open this publication in new window or tab >>Perception of time to contact of slow- and fast-moving objects using monocular and binocular motion information
2018 (English)In: Attention, Perception & Psychophysics, ISSN 1943-3921, E-ISSN 1943-393X, Vol. 80, no 6, p. 1584-1590Article in journal (Refereed) Published
National Category
Psychology (excluding Applied Psychology)
Identifiers
urn:nbn:se:uu:diva-387266 (URN)10.3758/s13414-018-1517-8 (DOI)000439488800021 ()29667039 (PubMedID)
Available from: 2018-04-17 Created: 2019-06-27 Last updated: 2019-06-27Bibliographically approved
Sjödén, B., Lind, M. & Silvervarg, A. (2017). Can a teachable agent influence how students respond to competition in an educational game?. In: André, Elisabeth; Baker, Ryan; Hu, Xiangen; Rodrigo, Ma. Mercedes T.; du Boulay, Benedict (Ed.), André, Elisabeth; Baker, Ryan; Hu, Xiangen; Rodrigo, Mercedes T.; du Boulay, Benedict (Ed.), Artificial Intelligence in Education: . Paper presented at 18th International Conference on Artificial Intelligence in Education (AIED), 2017, June 28 – July 1, Wuhan, China (pp. 347-358). Springer
Open this publication in new window or tab >>Can a teachable agent influence how students respond to competition in an educational game?
2017 (English)In: Artificial Intelligence in Education / [ed] André, Elisabeth; Baker, Ryan; Hu, Xiangen; Rodrigo, Mercedes T.; du Boulay, Benedict, Springer, 2017, p. 347-358Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Springer, 2017
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 10331
National Category
Human Computer Interaction
Identifiers
urn:nbn:se:uu:diva-335356 (URN)10.1007/978-3-319-61425-0_29 (DOI)000434475300029 ()978-3-319-61424-3 (ISBN)978-3-319-61425-0 (ISBN)
Conference
18th International Conference on Artificial Intelligence in Education (AIED), 2017, June 28 – July 1, Wuhan, China
Available from: 2017-06-23 Created: 2017-12-04 Last updated: 2018-10-22Bibliographically approved
Daniels, M., Cajander, Å., Eckerdal, A., Lind, M., Nylén, A., Clear, T. & McDermott, R. (2015). Competencies for paradigm shift "survival". In: Proc. 45th ASEE/IEEE Frontiers in Education Conference: . Paper presented at FIE 2015, October 21–24, El Paso, TX (pp. 1424-1429). Piscataway, NJ: IEEE Press
Open this publication in new window or tab >>Competencies for paradigm shift "survival"
Show others...
2015 (English)In: Proc. 45th ASEE/IEEE Frontiers in Education Conference, Piscataway, NJ: IEEE Press, 2015, p. 1424-1429Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Press, 2015
National Category
Computer and Information Sciences Educational Sciences
Identifiers
urn:nbn:se:uu:diva-269118 (URN)10.1109/FIE.2015.7344255 (DOI)000371705200240 ()978-1-4799-8453-4 (ISBN)
Conference
FIE 2015, October 21–24, El Paso, TX
Available from: 2015-10-24 Created: 2015-12-14 Last updated: 2018-01-10Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-1916-282x

Search in DiVA

Show all publications