49:(more than 15 of which exist in the cortex) for properties like color, edge orientation, speed of motion, and direction of motion. These base representations rely on fixed operations performed uniformly over the entire field of visual input, and do not make use of object-specific knowledge, task-specific knowledge, or other higher-level information.
60:
Ullman lists the following as examples of visual operators: shifting the processing focus, indexing a salient item for further processing, spreading activation over an area delimited by boundaries, tracing boundaries, and marking a location or object for future reference. When combined into visual
52:
The visual routines proposed by Ullman are high-level primitives which parse the structure of a scene, extracting spatial information from the base representations. These visual routines are composed of a sequence of elementary visual operators specific to the task at hand. Visual routines differ
64:
A number of researchers have implemented visual routines for processing camera images, to perform tasks like determining the object a human in the camera image is pointing at. Researchers have also applied the visual routines approach to artificial map representations, for playing real-time 2D
45:" stage during which high-level primitives dubbed "visual routines" extract the desired information from the base representations. In humans, the base representations generated during the bottom-up stage correspond to
61:
routines, these elementary operators can be used to perform relatively sophisticated spatial tasks such as counting the number of objects satisfying a certain property, or recognizing a complex shape.
46:
69:. In those cases, however, the map of the video game was provided directly, alleviating the need to deal with real-world perceptual tasks like
192:
Aste, Marco; Rossi, Massimo; Cattoni, Roldano; Caprile, Bruno (1998-06-01). "Visual routines for real-time monitoring of vehicle behavior".
42:
38:
168:
99:
53:
from the fixed operations of the base representations in that they are not applied uniformly over the entire
37:'s task of perceiving shape properties and spatial relations is split into two successive stages: an early "
116:
Huang, J.; Wechsler, H. (April 2000). "Visual routines for eye location using learning and evolution".
206:
151:
Johnson, M. P. (August 1996). "Automated creation of visual routines using genetic programming".
273:
201:
41:" state during which base representations are generated from the visual input, and a later "
8:
227:
174:
70:
219:
164:
133:
231:
211:
178:
156:
125:
57:--- rather, they are only applied to objects or areas specified by the routines.
246:
267:
223:
160:
137:
34:
26:
54:
215:
74:
129:
66:
30:
153:
Proceedings of 13th
International Conference on Pattern Recognition
254:
MIT Computer
Science and Artificial Intelligence Laboratory
23:
is a means of extracting information from a visual scene.
191:
16:
Means of extracting information from a visual scene.
100:"Ullman's Visual Routines, and Tekkotsu Sketches"
265:
118:IEEE Transactions on Evolutionary Computation
115:
205:
155:. Vol. 1. pp. 951–956 vol.1.
150:
266:
94:
92:
90:
13:
14:
285:
87:
29:, in his studies on human visual
247:"Visual Routines and Attention"
244:
194:Machine Vision and Applications
238:
185:
144:
109:
1:
80:
7:
10:
290:
33:, proposed that the human
161:10.1109/ICPR.1996.546164
216:10.1007/s001380050086
130:10.1109/4235.843496
71:object recognition
170:978-0-8186-7282-8
281:
258:
257:
251:
242:
236:
235:
209:
189:
183:
182:
148:
142:
141:
113:
107:
106:
104:
96:
47:retinotopic maps
289:
288:
284:
283:
282:
280:
279:
278:
264:
263:
262:
261:
249:
245:Rao, Satyajit.
243:
239:
190:
186:
171:
149:
145:
114:
110:
102:
98:
97:
88:
83:
17:
12:
11:
5:
287:
277:
276:
260:
259:
237:
207:10.1.1.48.5736
184:
169:
143:
108:
85:
84:
82:
79:
77:compensation.
21:visual routine
15:
9:
6:
4:
3:
2:
286:
275:
274:Visual system
272:
271:
269:
255:
248:
241:
233:
229:
225:
221:
217:
213:
208:
203:
199:
195:
188:
180:
176:
172:
166:
162:
158:
154:
147:
139:
135:
131:
127:
123:
119:
112:
101:
95:
93:
91:
86:
78:
76:
72:
68:
62:
58:
56:
50:
48:
44:
40:
36:
35:visual system
32:
28:
27:Shimon Ullman
24:
22:
253:
240:
200:(1): 16–23.
197:
193:
187:
152:
146:
124:(1): 73–82.
121:
117:
111:
63:
59:
55:visual field
51:
25:
20:
18:
67:video games
81:References
224:0932-8092
202:CiteSeerX
138:1089-778X
75:occlusion
39:bottom-up
31:cognition
268:Category
232:25480778
43:top-down
179:1701864
230:
222:
204:
177:
167:
136:
250:(PDF)
228:S2CID
175:S2CID
103:(PDF)
220:ISSN
165:ISBN
134:ISSN
73:and
212:doi
157:doi
126:doi
270::
252:.
226:.
218:.
210:.
198:11
196:.
173:.
163:.
132:.
120:.
89:^
19:A
256:.
234:.
214::
181:.
159::
140:.
128::
122:4
105:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.