We find results similar to those of conjunctive and adaptive fusions. However, we do not find unclassified pixels. While conjunctive fusion imposes the unanimity of the sources to decide to assign a pixel to a class, quantified adaptive fusion needs only a majority of sources in agreement to carry out the classification of the pixel. If none of the other sources formulates an opinion, then only one source will be enough to choose to assign the pixel to such or such class .Searching the greatest consensus among the sources, but without imposing the unanimity, makes it possible to classify the pixels that conjunctive fusion could not classify.

However, the result remains very close to that of conjunctive fusion because quantified adaptive fusion, such as we modified it, preserves a largely conjunctive behaviour on the spectral bands for which the unanimity is always reached (except for 1.21% of the pixels).

Table 33: Quantified adaptive fusion of the spectral bands MSS4 to MSS7.

Rates of classification obtained
Class	Number of pixels   correctly classified (A)	Number of pixels in samples      (B)	Rate of pixels     correctly classified (A/B)
1	171	459	37.25%
2	241	459	52.51%
3	122	306	39.87%
4	206	391	52.69%
5	274	459	59.69%
6	281	459	61.22%
7	341	459	74.29%
8	308	459	67.10%
9	171	459	37.25%
TOTAL	2115	3910	54.09%