CiteSeerX — Table search results

Results 1 - 10 of 7,628

Table 4 Summary of the natural scene image data set.

in Ml-knn: A lazy learning approach to multi-label learning

by Min-ling Zhang, Zhi-hua Zhou 2007

"... In PAGE 12: ... The experimental data set consists of 2 000 natural scene images, where a set of labels is manually assigned to each image. Table4 gives the detailed descrip- tion of the number of images associated with difierent label sets, where all the possible class labels are desert, mountains, sea, sunset and trees. The number of images belonging to more than one class (e.... ..."

Cited by 2

Table 1. Usefulness of character segmenta- tion in natural scene images

in Character Segmentation-by-Recognition Using Log-Gabor Filters

by Céline Mancas-thillou, Bernard Gosselin

"... In PAGE 3: ... Some results In this section, we present some results under various forms. Table1 shows the increase of the recognition rate for our tested database. We use the ICDAR2003 public sample database, which includes 171 already detected text areas, with some examples even not recognizable by hu- mans.... ..."

Table 2 : Repeatability study : robustness against natural noise Scene

in Definition of

by Cédric Lemaitre, Johel Miteran, Jiri Matas

"... In PAGE 6: ...cene). Some examples are depicted on Fig. 7. For each image, 2 sections have been analyzed by a human expert and our algorithm in order to determine the centre position and the width of section. The errors introduced by our method (absolute value of differences between human measurements and filter responses) are presented in the Table 1 and Table2 . The error measured on the axis position and the curvilinear region width is from 1 to 2 pixels in many cases.... ..."

Table 2. Correlation between orderings of natural scenes made by observers and the two templates for each spatial envelope property.

in Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

by Aude Oliva, Antonio Torralba 2001

"... In PAGE 17: ... Agreement evaluates the difficulty of the ordering task and the concordance of the criteria used by the subjects. Results of Table2 show high correlations for the three spatial envelope properties. The average correlation be- tween the DST (unlocalized spectral components) and the subjects is 0.... ..."

Cited by 80

Table XIII. List of Queries Used in Research Original Queries Containing Query Operators Simplified Query (i.e., Query Operators Submitted by Search Engine Users Removed) Used for Comparison daktarin AND nail daktarin nail wallpaper AND nature scenes wallpaper nature scenes

in Coverage, Relevance, and Ranking: The Impact of Query Operators on . . .

by Caroline M. Eastman, Bernard J. Jansen 2003

Cited by 20

Table 1: Normalized vertical coe cients of scale 32 32 of images with (a) random natural scenes (without people), (b) pedestrians.

in A Trainable System for People Detection

by Michael Oren, Constantine Papageorgiou, Pawan Sinha, Edgar Osuna, Tomaso Poggio 1997

"... In PAGE 4: ... Several conclusions can be drawn from the tables. Table1 (a) shows that the process of averaging the coe cients within the pattern and then in the en- semble does not create spurious patterns. The av- erage values of the non-pedestrian coe cients are near 1 since these are random images that do not share any common pattern.... ..."

Cited by 6

Table 4. Summary of large natural scene experiment. The training images were drawn at random from the pool of available images, with the remaining images serving as a disjoint set of test images.

in Hierarchical Discriminant Analysis for Image Retrieval

by Daniel L. Swets, John (Juyang) Weng 1999

Cited by 32

Table 2. Summary of large natural scene experiment. The training images were drawn at random from the pool of available images, with the remaining images serving as a disjoint set of test images.

in SHOSLIF-O: SHOSLIF for Object Recognition and Image Retrieval (Phase II)

by Daniel L. Swets, John J. Weng 1995

"... In PAGE 19: ... Following training, the system was tested using a disjoint test set. A summary of the makeup of the test and the results are shown in Table2 . The instances where the retrieval failed were due... ..."

Cited by 6

Table 2. Summary of large natural scene experiment. The training images were drawn at random from the pool of available images, with the remaining images serving as a disjoint set of test images.

in SHOSLIF-O: SHOSLIF for Object Recognition and Image Retrieval (Phase II)

by Daniel L. Swets, John J. Weng 1995

Cited by 6

Table 2. Summary of large natural scene experiment. The training images were drawn at random from the pool of available images, with the remaining images serving as a disjoint set of test images.

in SHOSLIF-O: SHOSLIF for Object Recognition and Image Retrieval (Phase II)

by Daniel Swets

"... In PAGE 20: ... Following training, the system was tested using a disjoint test set. A summary of the makeup of the test and the results are shown in Table2 . The instances where the retrieval failed were due... ..."

Results 1 - 10 of 7,628

Tools

Table 4 Summary of the natural scene image data set.

Table 1. Usefulness of character segmenta- tion in natural scene images

Table 2 : Repeatability study : robustness against natural noise Scene

Table 2. Correlation between orderings of natural scenes made by observers and the two templates for each spatial envelope property.

Table XIII. List of Queries Used in Research Original Queries Containing Query Operators Simplified Query (i.e., Query Operators Submitted by Search Engine Users Removed) Used for Comparison daktarin AND nail daktarin nail wallpaper AND nature scenes wallpaper nature scenes

Table 1: Normalized vertical coe cients of scale 32 32 of images with (a) random natural scenes (without people), (b) pedestrians.

Table 4. Summary of large natural scene experiment. The training images were drawn at random from the pool of available images, with the remaining images serving as a disjoint set of test images.

Table 2. Summary of large natural scene experiment. The training images were drawn at random from the pool of available images, with the remaining images serving as a disjoint set of test images.

Table 2. Summary of large natural scene experiment. The training images were drawn at random from the pool of available images, with the remaining images serving as a disjoint set of test images.

Table 2. Summary of large natural scene experiment. The training images were drawn at random from the pool of available images, with the remaining images serving as a disjoint set of test images.