Abstract
Images are about pictures. Percepts are about information. People need images. Machines do not. This paper suggests that it may be possible for machines to perceive things, not just register images in real time. This goal inspired our search for methods that might work in real time to perceive their world. In our brains, the image is processed separately in different parts of the brain, and the results of those parallel operations are somehow fused to form the percept. We have done extensive development of a spectral segmentation of images using “Artificial Color” based on the way animals use spectral information. That research showed that there is a massively parallel approach to recognize targets or their background using Fourier texture discrimination. In this paper, a Fourier-based system that uses nonlinear discrimination to recognize shape, size, pose, and location of a target in a scene is discussed. The sought-after conversion of that information into an Artificial Percept in which a “cartoon” of the situation is formed with labeled targets giving their appearance (pose and size) and location. This is a primitive percept. The machine no longer has an image. Instead it “knows” what targets of interest are in the field, where they are, and their range and pose.
Similar content being viewed by others
References
Caulfield HJ (2001) Independent Task Fourier filters. Opt Eng 40:2414–2418
Caulfield HJ (2002) Templates for invention in the mathematical and physical sciences with applications to optics. In: Caulfield HJ (ed) Optical information processing: a tribute to Adolf Lohmann. SPIE Press, Bellingham, pp 131–148
Caulfield HJ (2003) Artificial Color. Neurocomputing 51:463–465
Caulfield HJ, Fu J, Yoo SM (2004) Artificial Color Image Logic. Inf Sci 167:1–7
Caulfield HJ, Fu J (2007) Holographic spectral image discrimination and segmentation. J Hologr Speckle 3:112–116
Caulfield HJ, Heidary K (2004) Margin Net: obtaining supergeneralization and target location by combining Fourier Correlation with Neural Networks. Opt Mem Neural Netw 13:15–25
Caulfield HJ, Heidary K (2005) The topology of discrimination with single layer perceptrons. Opt Mem Neural Netw 14:15–26
Caulfield HJ, Heidary K (2005) Exploring margin setting for good generalization in multiple class discrimination. Pattern Recognit 38:1225–1238
Caulfield HJ, Karavolos A, Ludman J (2004) Improving optical Fourier pattern recognition by accommodating the missing information. Inf Sci 162:35–48
Fu J (2004) Joint exploration of artificial color and margin setting: an innovative approach in color image segmentation, Ph.D. Dissertation, University of Alabama in Huntsville, Huntsville, AL
Fu J, Caulfield HJ (2007) Designing spectral sensitivity curves for use with Artificial Color. Pattern Recognit 40:2251–2260
Fu J, Caulfield HJ (2007) Applying color discrimination to polarization discrimination in images. Opt Comm 272:362–366
Fu J, Caulfield HJ, Pulusani SR (2004) Artificial Color vision: a preliminary study. J Elec Imaging 13:553–558
Fu J, Caulfield HJ, Wu D, Tadesse W (2010) Hyperspectral image analysis using Artificial Color. J Appl Remote Sens 4:043514
Fu J, Caulfield HJ, Wu D, Montgomery T (2010) Effects of hyperellipsoidal decision surfaces on image segmentation in Artificial Color. J Electron Imaging. doi:10.1117/1.3377146
Heidary K, Caulfield HJ (2005) Application of supergeneralized matched filters to target classification. Appl Opt 44:47–54
Heidary K, Caulfield HJ (2006) Discrimination among similar looking noisy color patches using Margin Setting. Opt Express 15:62–75
Knill DC, Richards W (1996) Perception as Bayesian inference. Cambridge University Press, Cambridge
Rao RPN, Olshausen BA, Lewicki MS (2002) Probabilistic models of the brain: perception and neural function (neural information processing). MIT Press, Cambridge
Rodriguez-Sanchez R, Garcia JA, Fdez-Valdivia J, Fdez-Vidal XR (2000) Origins of illusory percepts in digital images. Pattern Recogn 33:2007–2017
Small K, Roth D (2010) Margin-based active learning for structured predictions. Int J Mach Learn Cyber 1:3–25
Solia SA, Leen TK, Muller KR (2000) Advances in Neural Information Processing Systems 12. MIT Press, Cambridge
Acknowledgments
This work is supported under a contract by the US Army AMRDEC in Huntsville, AL.
Author information
Authors and Affiliations
Corresponding author
Appendix: Margin Setting Algorithm
Appendix: Margin Setting Algorithm
Sample feature vectors \( A = \{ \vec{x}_{1} , \ldots ,\vec{x}_{n} \} \subset [0,\;1]^{q} \subset R^{q} \) taking from the target class and the sample vectors \( B_{l} = \{ \vec{y}_{l,1} , \ldots ,\vec{y}_{{l,m_{l} }} \} \subset [0,\;1]^{q} \subset R^{q} \) (\( l = 1, \ldots ,k \)) taking from the other \( k \) objects. Denote \( B = \bigcup\limits_{l = 1}^{k} {B_{l} } \).
1.1 Notation:
Rand (\( F \)): random numbers taking from distribution \( F \).
Unif (\( D \)): uniform distribution function on set \( D \).
Card (\( D \)): the figure of merit of set \( D \).
\( [a,\;b]^{q} \; \): a \( q \)-dimensional cube.
\( O(\vec{z},\,R) \): a \( q \)-dimensional ball centered at \( \vec{z} \) with radius \( R \).
\( I \): designed number of generations.
\( \varepsilon \): designed error tolerance.
\( s \): designed number of samples taken for each generation.
\( \delta \): designed size of perturbation.
\( L \): designed number of mutations for each generation.
1.2 Algorithm:
-
1.
Compute \( N \equiv \) Card(\( A \)), and set \( i = 0 \).
-
2.
\( i: = i + 1 \). If \( i > I \) or Card(\( A \))/\( N \)<\( \varepsilon \), output \( \{ (\vec{c}_{j} ,\,r_{j} ;\,N_{j} ):\;j = 1, \ldots ,i - 1\} \), and stop!
-
3.
Take \( \vec{c}_{i,1} , \ldots ,\vec{c}_{i,s} \) from Rand(Unif(\( [0,\;1]^{q} \))) and set \( t_{i} = 0 \). For \( j = 1, \ldots ,s \), compute \( r_{i,j} = \mathop {\hbox{min} }\limits_{{\vec{y} \in B}} |\vec{y} - \vec{c}_{i,j} | \). If \( N_{i,j} \) \( \equiv \) Card(\( A \cap O(\vec{c}_{i, j} ,\,r_{i, j} ) \) ) = 0, discard ball \( O(\vec{c}_{i,j} ,\,r_{i,j} ) \); otherwise, \( t_{i} : = t_{i} + 1 \), and record \( (\vec{c}_{i,j} ,r_{i,j} ;N_{i,j} ) \).
-
4.
If \( t_{i} = 0 \), record \( (\vec{c}_{i} ,\,r_{i} ;\,N_{i} ) = (\vec{0},\,0;\,0) \), go to step 2; otherwise, for \( \{ (\vec{c}_{i,j} ,\,r_{i,j} ;\,N_{i,j} ):\;j = 1,\; \ldots ,t_{i} \} \), compute
-
5.
Take \( v_{i} \) from Rand(Unif(\( [0,\;1] \))), if \( v_{i} \in [\sum\nolimits_{j = 1}^{{\ell_{i,0} - 1}} {w_{i,j} ,\;\sum\nolimits_{j = 1}^{{\ell_{i,0} }} {w_{i,j} } } ] \) for some \( \ell_{i,0} \in \{ 1,\,2, \cdots ,t_{i} \} \), Set \( N_{i} = N_{{i,\ell_{i,0} }} \) and the corresponding ball as \( O(\vec{c}_{i} ,\,r_{i} ) \); and discard all the other balls. Set \( l = 1 \).
-
6.
Take \( \vec{s}_{l} \) from Rand(Unif(\( [ - \delta ,\;\delta ]^{q} \))), mutate \( \vec{c}_{i} \) to \( \vec{c}_{i}^{1} = \vec{c}_{i} + \vec{s}_{l} \), and compute \( r_{i,j} = \mathop {\hbox{min} }\limits_{{\vec{y} \in B}} |\vec{y} - \vec{c}_{i,j} | \). If Card(\( A \cap O(\vec{c}_{i}^{1} ,\,r_{i}^{1} ) \))\( \le N_{i} \), record \( (\vec{c}_{i} ,\,r_{i} ;N_{i} ) \) and set \( A: = A\backslash O(c^{i} ,R^{i} ) \), go to step 2; otherwise, \( N_{i} : = \)Card(\( A \cap O(\vec{c}_{i}^{1} ,\,r_{i}^{1} ) \)), \( \vec{c}_{i} : = \vec{c}_{i}^{1} \), \( r_{i} : = r_{i}^{1} \) and \( l: = l + 1 \). If \( l > L \), record \( (\vec{c}_{i} ,\,r_{i} ;N_{i} ) \) and set \( A: = A\backslash O(c^{i} ,R^{i} ) \), go to step 2; otherwise, go to step 6.
Rights and permissions
About this article
Cite this article
Fu, J., Caulfield, H.J. & Glenn, C. Primitive attempt to turn images into percepts. Int. J. Mach. Learn. & Cyber. 5, 963–970 (2014). https://doi.org/10.1007/s13042-013-0184-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-013-0184-2