关于「什么先跳出来:视觉搜索与显著性图谱」,《计算美学与界面认知工程》给出的定量结论是什么?
结论:视觉搜索的速度取决于目标在可并行计算的特征上与干扰项的相对差异:差异足够大时目标「跳出」,没有差异时退化为逐项搜索,引导搜索介于两者之间,模拟中的斜率与 \(50\,\Phi(-d'/\sqrt2)\) 的预测一致。伊蒂—科赫—尼布尔模型的结构(九级金字塔、\(c\in\{2,3,4\}\)、\(\delta\in\{3,4\}\)、42 张特征图、\(\mathcal N(\cdot)\)、胜者全得加返回抑制)核对无误;纯标准库的实现显示,在这个模型中,一个按钮的颜色唯一性可以把它从第 18 次注意转移提前到第 1 次。但模型只描述底层显著性,原文自己说明其轨迹不一定与人的注视相似;网页上的中央与左上偏差、任务、文字与人脸往往更重要。
数据口径:书中以标注框区分已发表的证据、可运行的 Python 计算(16 段程序)、原典与作者的模型和假说;书中所有页面、品牌与数据都是虚构或模拟的。
对照数据表
下表数字由本章 Python 程序原样打印,可重新运行复现。 程序只用 Python 标准库与结论吻合的打印值: 18, 42
| layout A, red CTA | 42 feature maps; saliency map 16 x 12 (level 4) |
| |=*+=============| | |
| |-=--=====-------| | |
| |++====-++-------| | |
| |++==+--++-------| | |
| |=*++++++====----| | |
| |=*++++++*@@@*---| | |
| |-=======--==--::| | |
| |-:------::::::::| | |
| |:::: | ...:.......| |
| |:::: | ...:.......| |
| |:: | .:...:...:...| |
| | | .:::.:::.......| |
| shift 1: cell (11, 5) S | 0.245 CTA button |
| shift 2: cell ( 1, 0) S | 0.165 logo |
| shift 3: cell ( 8, 5) S | 0.162 CTA button |
| shift 4: cell ( 1, 5) S | 0.149 hero photo |
| shift 5: cell ( 3, 4) S | 0.139 hero photo |
| shift 6: cell ( 8, 2) S | 0.135 white space |
| the CTA button is first attended at shift 1 | |
| peak S: CTA button 0.245, logo 0.165, hero photo 0.149, body text 0.134, card 1 0.082 | |
| layout B, grey CTA | 42 feature maps; saliency map 16 x 12 (level 4) |
| shift 1: cell ( 1, 0) S | 0.274 logo |
| shift 2: cell ( 2, 5) S | 0.183 hero photo |
| shift 3: cell ( 6, 5) S | 0.176 hero photo |
| shift 4: cell ( 4, 4) S | 0.172 hero photo |
| shift 5: cell ( 7, 3) S | 0.159 hero photo |
| shift 6: cell ( 1, 3) S | 0.158 hero photo |
查看完整验算程序
# Itti-Koch-Niebur (1998) saliency, synthetic 256 x 192 landing page, standard
# library only. Nine dyadic Gaussian levels (0-8); centre c in {2,3,4}, surround
# s = c + d, d in {3,4}; 6 intensity, 12 colour, 24 orientation maps (42 in all);
# N(.) = scale to [0,1], multiply by (1 - mean of the other local maxima)^2; conspicuity
# maps summed at level 4; S = (N(I) + N(C) + N(O))/3. Simplifications: orientation =
# |oriented second difference| instead of Gabor filters, nearest-neighbour expansion,
# and an argmax WTA with disk-shaped inhibition of return (radius 1/6 of the smaller
# image side) instead of integrate-and-fire neurons. Layout A: red call-to-action
# (CTA) button; layout B: the same button in grey of equal intensity I = (r+g+b)/3.
import math # math.fsum: same float sums on Python 3.8-3.13
W, H = 256, 192
BOXES = [("nav bar", 0, 0, 256, 16, (.15, .15, .17)),
("logo", 8, 3, 40, 13, (.95, .55, .1)),
("hero photo", 8, 24, 124, 100, (.35, .55, .6)),
("sun in photo", 84, 34, 100, 50, (.98, .85, .2)),
("headline", 136, 28, 248, 36, None), ("body text", 136, 44, 248, 64, None),
("CTA button", 136, 76, 196, 92, (.85, .1, .1)),
("2nd button", 204, 76, 248, 92, (.9, .9, .9))]
BOXES += [(f"card {k + 1}", 8 + 62 * k, 116, 62 * k + 64, 180, (.93, .93, .93))
for k in range(4)]
THUMB = ((.75, .8, .85), (.85, .8, .75), (.8, .85, .78), (.82, .8, .86))
def page(cta):
img = [[(.97, .97, .97)] * W for _ in range(H)]
for name, x0, y0, x1, y1, col in BOXES:
col = cta if name == "CTA button" else col
for y in range(y0, y1):
for x in range(x0, x1):
if col:
img[y][x] = col
elif x % 7 < 4 and (name == "headline" or y % 7 < 4): # text strokes
img[y][x] = (.1, .1, .1) if name == "headline" else (.35, .35, .35)
for k in range(4): # card thumbnails and labels
for y in range(122, 160):
for x in range(14 + 62 * k, 58 + 62 * k):
img[y][x] = THUMB[k]
for y in range(166, 174):
for x in range(14 + 62 * k, 50 + 62 * k):
if x % 5 < 3:
img[y][x] = (.4, .4, .4)
return img
def down(m): # blur with [1 4 6 4 1]/16, then keep every 2nd pixel
h, w = len(m), len(m[0]); k = (1, 4, 6, 4, 1)
fs = math.fsum
rows = [[fs(k[j] * r[min(max(x + j - 2, 0), w - 1)] for j in range(5)) / 16
for x in range(0, w, 2)] for r in m]
return [[fs(k[j] * rows[min(max(y + j - 2, 0), h - 1)][x] for j in range(5)) / 16
for x in range(len(rows[0]))] for y in range(0, h, 2)]
def pyramid(m):
p = [m]
while len(p) < 9:
p.append(down(p[-1]))
return p
def diff(c, s, sign=1): # |c (-) s|: expand s to the size of c, subtract
fy, fx = len(s) / len(c), len(s[0]) / len(c[0])
return [[abs(c[y][x] - sign * s[int(y * fy)][int(x * fx)]) for x in range(len(c[0]))]
for y in range(len(c))]
def N(m):
mx = max(max(r) for r in m) or 1.0
m = [[v / mx for v in r] for r in m]; h, w = len(m), len(m[0]); peaks = []
for y in range(h):
for x in range(w):
v = m[y][x]
if 0 < v < 1 and all(v >= m[j][i] for j in range(max(y - 1, 0), min(y + 2, h))
for i in range(max(x - 1, 0), min(x + 2, w))):
peaks.append(v)
f = (1 - math.fsum(peaks) / len(peaks)) ** 2 if peaks else 1.0
return [[v * f for v in r] for r in m]
def to4(m): # average-pool any level to 16 x 12
f = len(m) // 12
return [[math.fsum(m[y * f + j][x * f + i] for j in range(f) for i in range(f)) / f**2
for x in range(16)] for y in range(12)]
def add(a, b):
return [[u + v for u, v in zip(r, q)] for r, q in zip(a, b)]
def orient(m, t): # oriented second difference, theta = 0/45/90/135
dy, dx = ((0, 1), (1, 1), (1, 0), (1, -1))[t]; h, w = len(m), len(m[0])
g = lambda y, x: m[min(max(y, 0), h - 1)][min(max(x, 0), w - 1)]
return [[abs(2 * g(y, x) - g(y - dy, x - dx) - g(y + dy, x + dx)) for x in range(w)]
for y in range(h)]
def saliency(img):
I = [[math.fsum(p) / 3 for p in r] for r in img]; imax = max(max(r) for r in I)
def opp(p, i):
if i < imax / 10:
return 0.0, 0.0
r, g, b = (v / i for v in p)
R, G, B = r - (g + b) / 2, g - (r + b) / 2, b - (r + g) / 2
Y = (r + g) / 2 - abs(r - g) / 2 - b
return max(R, 0) - max(G, 0), max(B, 0) - max(Y, 0)
op = [[opp(p, i) for p, i in zip(r, ri)] for r, ri in zip(img, I)]
PI = pyramid(I); PRG = pyramid([[o[0] for o in r] for r in op])
PBY = pyramid([[o[1] for o in r] for r in op])
PO = [[orient(PI[l], t) if l >= 2 else None for l in range(9)] for t in range(4)]
zero = [[0.0] * 16 for _ in range(12)]; Ib, Cb, Ob = zero, zero, [zero] * 4; n = 0
for c in (2, 3, 4):
for s in (c + 3, c + 4):
Ib = add(Ib, to4(N(diff(PI[c], PI[s]))))
rg, by = to4(N(diff(PRG[c], PRG[s], -1))), to4(N(diff(PBY[c], PBY[s], -1)))
Cb = add(Cb, add(rg, by))
Ob = [add(Ob[t], to4(N(diff(PO[t][c], PO[t][s])))) for t in range(4)]
n += 7 # 1 intensity + 2 colour + 4 orientation maps
Ob = [N(o) for o in Ob]; O = add(add(Ob[0], Ob[1]), add(Ob[2], Ob[3]))
S = add(add(N(Ib), N(Cb)), N(O))
return [[v / 3 for v in r] for r in S], n
def label(x, y): # level-4 cell -> page element under its centre
px, py = 16 * x + 8, 16 * y + 8
for name, x0, y0, x1, y1, _ in reversed(BOXES):
if x0 <= px < x1 and y0 <= py < y1:
return name
return "white space"
def scanpath(S, k=6, r=2):
S = [row[:] for row in S]; out = []
for _ in range(k):
v, y, x = max((S[y][x], y, x) for y in range(12) for x in range(16))
out.append((x, y, v))
for j in range(12):
for i in range(16):
if (i - x) ** 2 + (j - y) ** 2 <= r * r:
S[j][i] = 0.0
return out
if __name__ == "__main__":
for tag, cta in (("A, red CTA", (.85, .1, .1)), ("B, grey CTA", (.35, .35, .35))):
S, n = saliency(page(cta))
print(f"layout {tag}: {n} feature maps; saliency map 16 x 12 (level 4)")
if tag[0] == "A":
mx = max(max(r) for r in S)
for r in S:
print(" |" + "".join(" .:-=+*#%@"[min(int(v / mx * 10), 9)] for v in r)
+ "|")
path = scanpath(S, k=40)
for i, (x, y, v) in enumerate(path[:6], 1):
print(f" shift {i}: cell ({x:2d},{y:2d}) S = {v:.3f} {label(x, y)}")
first = next(i for i, (x, y, v) in enumerate(path, 1)
if label(x, y) == "CTA button")
print(f" the CTA button is first attended at shift {first}")
peak = {}
for y in range(12):
for x in range(16):
peak[label(x, y)] = max(peak.get(label(x, y), 0.0), S[y][x])
print(" peak S: " + ", ".join(f"{k} {peak[k]:.3f}" for k in
("CTA button", "logo", "hero photo", "body text", "card 1")))唯一数据源与引用
范雅福(Fan, Y.). (2026). 《计算美学、视觉显著性图谱与人机界面认知工程》第 3 章「什么先跳出来:视觉搜索与显著性图谱」(版本 1.0.0). 5D Library. https://doi.org/10.5281/zenodo.23836258
DOI: 10.5281/zenodo.23836258 · 阅读本章所在专著 · 5DL-B-046 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026046,
author = {Fan, Yafu},
title = {Computational Aesthetics, Visual Saliency Maps and Cognitive Ergonomics in User Interface Design},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
doi = {10.5281/zenodo.23836258},
url = {https://doi.org/10.5281/zenodo.23836258}
}